As someone who owns a weathered copy of Hackers and Painters and routinely says things like “a rare miss from pg”, I think this is a big miss from pg.
And the real shame is that he gets so close: he talks about discovery, about the intersection of science and technology and the broader world, he identifies the importance of doing things to learn enough to write about them, and most importantly: having an outrageous question with a real and alarming insight lurking around the corner as an answer and thereby avoids vaporous rhapsodizing.
So I’ll ask an outrageous question about which pg has both deep insight and over a decade of lived experience to ground an answer on: is YC still a good thing? I’ll ask a few corollary questions to illustrate.
He talks about the kinds of tests you hack to get ahead in some vague elsewhere: is getting ahead in YC, or the Valley, or the technology business still about merit and capability and being relentlessly resourceful rather than optics, connections, and flexibility? Is it about garages with Ethernet cables snaking everywhere more or less than knowing one’s way around the Rosewood Sand Hill?
His first citation as a reviewer is Sam Altman: is @sama still his pick for most capable founder and best person to guide the sprawling empire that YC sits at the heart of?
I don’t find any of those things obvious, and I think a candid essay about a set of very timely questions would be the most important essay he’d ever written.
Sam went through the garage startup stage in 2005-2007, and again in 2015-2017 with OpenAI. He was good at it -- I saw both firsthand. At OpenAI he was scrounging GPUs when that's what we needed most, and wangled a prototype DGX-1 long before you could buy one. More importantly, he convinced people to leave multi-million dollar salaries at Google & DeepMind for a tiny startup no one had heard of. Now OpenAI needs to build a trillion dollars of infrastructure and lobby governments for favorable regulation, so he's doing whatever that involves. It wouldn't make sense for him to be running Ethernet cables today.
YC's public content focuses on early-stage startups. Should it have more on late-stage startups? Maybe, but it doesn't seem as impactful. The reason to produce public content is that it can scale to reach more people than the partners can talk to one-on-one. There are fewer late-stage startups, so the scaling problem hasn't hit yet. YC follows its own advice of doing things in ways that don't scale until scaling becomes necessary.
One set of outrageous if solicited questions to a living legend seems enough for one day, and I'm very aware of the amount of non-public, first-hand knowledge I'm addressing here, so please take this in the highly respectful spirit in which it is intended from someone who recognizes that their entire career and adult life have been shaped by your and pg's achievements.
I do not find it at all obvious that either a trillion dollars in private investment or aggressive lobbying around regulation favorable to a particular for-profit entity are necessary or even possible paths to outcomes that are globally good for humanity or locally good for the community of people who spend time in threads like these.
I don't think that I'm part of a small minority in finding those means very dubious ways to accomplish things, the ends to which those means are being put of questionable public-mindedness, or the secrecy and apparent subterfuge with which this to all external appearances is being done acceptable ways to wield vast power.
I don't know if you'd make this argument, but others have when arguing for the same outcomes, so if I'm addressing them and not you please excuse me: we have institutions with a mandate from the public to deploy wartime budgets on Manhattan Project-scale undertakings attended by extreme risk. This cannot be ethically, morally, or legally delegated to unelected and unappointed individuals or private for-profit institutions via what was once called corruption.
Clearly I speak only for myself, but many others with far better credentials are saying similar things, in many cases much more stridently.
FWIW I was about to post this on a now (probably appropriately) flagged remark about retribution for dissent regarding critical remarks here and it went under while I was typing. I felt it was worth posting here to make it plain to anyone who is thinking but not saying what the other poster green-named (as my comment is probably one of the most "critical"-sounding on the thread):
"
I've been probingly questioning of pg's essay on this very thread, and as he requested I asked a few questions that can be fairly described as "outrageous". I think they're in the spirit of his call for outrageous questions, but they aren't "softballs".
Trevor challenged me on this, and I respectfully disagreed with his assertions in the same breath as acknowledging the almost limitless power of the YC network in my profession.
I did this not because I have any desire to be ground under the boot of the YC network, but because I trust @pg and Jessica and @tlb and (especially these days) @dang. My questions are about whether or not their good intentions might have gone awry, why they might or might not be worried about that: not whether or not they have always had and still have good intentions.
I've been hanging around here for like 16 years, and I don't fear retribution for respectful dissent at all. This is in sharp contrast to some other parts of the industry that I've wandered through.
"
While comparing ordinary human activity to language modeling is perhaps the greatest intellectual cliche of 2024, what PG describes in the essay-writing process itself essentially boils down to beam search. Autocomplete, find wrongness, backtrack, predict more consistent series of next tokens. The fact that only one of those options is actually reflected on the screen doesn't change the fact that the writer is probability-weighting continuations in their head.
I remember running across a tweet that said, in essence, you always have access to your own optimal policy if you simply ask. A similar technique might be the key to wresting good ideas from an ambiguous starting point: "What would be the most consistent answer to the original question, given what I've learned and written so far?"
Maybe that's the process PG describes themselves, but I think that the amount of different "processes" or "human equivalent to LLM decoding/sampling techniques" used by humans is likely very large - far larger than the number of techniques available to LLMs today.
Today within LLMs, there typicality sampling, contrastive search, top-p/top-k (nucleus sampling), and a whole massive amount of other more obscure techniques which didn't make it into huggingfaces model.generate() function.
I believe that the ontological configuration of humans has wide variety. As such, I believe that humans go through a diverse and vibrant amount of different writing processes - and often radically different processes can still result in excellent works!
Specifically, beam search is really only good at dealing with sequence-sequence tasks, i.e. summarization or translation. It's also horribly, horribly inefficient in the worst case scenarios. That said, it's also the only good way we know of for enforcing sequence level constraints (i.e. like this https://huggingface.co/blog/constrained-beam-search)
"It probably wouldn't be about this year's lipstick colors."
Why not? "Death of a Pig" didn't convey any new scientific ideas, and might not even have been surprising in any kind of intellectual way.
You could title this piece "Great Essays" and it would be entirely defensible. But Graham gave himself a higher goal here, and I don't think he's really presented a recipe for writing the Best essay. Look what he's up against: Baldwin, Didion, Oliver Sacks; it's easier to come up with examples of great essays that don't set out to develop surprising new ideas, and that probably didn't start out with a mischievous look in the author's eyes.
I'm not saying this isn't good advice for developing great essays, just that it's advice that narrows the solution space a bit much.
This wouldn't be a classic Paul Graham essay without his two great hallmarks -- many passages of provocative valuable insights -- paired with periodic, bewildering attempts to sabotage his own argument.
I'll add some fan mail later if necessary (because I do get value from reading him), but for the moment, here's where I believe he went off course.
1. When he says the best essays are "ineffective," he's chosen the wrong word. They are "premature." They arrive before the world is fully ready to acknowledge their power. But they catch at least a modest following right away. And then their work grows and grows.
2. Essays about new technology can be quite powerful, and that's Graham's wheelhouse, so it's fine for him to talk up this cohort. But any serious survey of legendary essays needs to look wider. The most powerful essays redefine our social, moral, political and religious norms. Here are a few favorites that didn't just win their year; they stood out for centuries.
70 AD: The Gospel of Mark. Chronologically the first book of the New Testament, and look what that unleashed
1778: Common Sense by Thomas Paine. The boldest, fiercest justification for the American Revolution, and one that's still a touchstone today for anyone with a deep interest in the theory or practice of democracy.
1963: Letter From Birmingham Jail by Martin Luther King. Worth being on the list simply for its effect on the U.S. civil rights movement; even more significant as the unbreakable tuning fork for any civil or human rights movement anywhere.
We'll keep inventing new technologies, because that's what humans are good at, and I'm sure many strong essays will ensue. But it's the redefining of our social institutions that's likely to make the future so incredibly different from today. Anyone who can write a prescient reflection about society's new rules will get my vote for "Great Essays."
Excellent point on "Death of a pig" by E.B White. It's the perfect example of a timeless essay, without a "big scientific idea".
For others unaware of it, that essay was written in 1948[1], go read it in full. It starts like this:
"I spent several days and nights in mid-September with an ailing pig and I feel driven to account for this stretch of time, more particularly since the pig died at last, and I lived, and things might easily have gone the other way round and none left to do the accounting."
Would also like to mention that the Elements of Style by William Strunk and E.B White is an all-time great book on non-fiction writing. It was required for my Newspaper Fundamentals class in college and I've used it so much since that the creases are wearing thin.
There's another fantastic book—On Writing Well—that is a recurring read for me. An aside—I was in one of the early programing bootcamps, The Starter League. My class was held in 37signals office. Jason Fried and some of the other 37signals designers were in this class with me. One day Jason stood up and answered a few questions. One of the other students asked him about books. He walked over to a closet and opened the door. There were hundreds of copies of On Writing Well. That's the book he'd gift to people.
That always struck me as interesting. Especially since he'd written (or co-authored) several books at that point.
[EDITED to add:] I don't know how close to identical this is to the Chronicle article; at the end it says "Adapted from an article written for The Chronicle of Higher Education"; my guess is that essentially nothing was changed, but I haven't tried to check.
It's a good read, but by its very nature invites the following sort of riposte. I'll indulge in just one.
> “Write with nouns and verbs, not with adjectives and adverbs,” they insist. (The motivation of this mysterious decree remains unclear to me.)
The motivation is so that ponderous language like
> Following the platitudinous style recommendations of Elements would make your writing better if you knew how to follow them
Might be edited to something like "Though many are mere platitudes, following the style recommendations of Elements would make your writing better if you knew how to follow them".
The sentence, as written, suggests that the platitudes, specifically, as opposed to any which might be less uhhhh, platitudinous, would make your writing better. I don't believe this was the author's intent.
Yeah, while I appreciate the little classic, "Elements of Style", it falls short[1]. As you say, "On Writing" is indeed a better practical guide -- just by reading the first 80 pages, you get a lot of value out of it.
Another book I love is, "Towards Clarity and Grace" by Joseph Williams and Gregory Colomb (there are several expensive editions of it with modified names, but any older version would do). I elaborated more on it here[1] in the past.
That’s a really great endorsement. I had Zinsser as a textbook for a non-fiction creative writing class in university. It was one of the only textbooks I never had a compunction to sell. Haven’t read it since then, but your comment will make me give it a re-read.
I want to be careful not to pummel a straw man, because it's sort of clear that Graham doesn't believe the Best essay must come from an exploration of science or of exciting new ideas (though most of the advice he gives is for that kind of essay). If I have a concern, I think it's about the chemistry his writing has with this community, how threads here will bleach it down to a game of prog-rock writing, trying to somehow outdo Darwin.
I think that Graham's essays have a special significance to HN, and that the community here has a tendency to project things Graham says further along a direction of HN-think than Graham intends in his writing, so that you can imagine threads about how the only contenders for "Best" essays, like, prove P!=NP or something.
I'm mostly motivated to comment by that phenomenon, not by the plain text of Graham's essay.
"Almost any question can get you a good essay. Indeed, it took some effort to think of a sufficiently unpromising topic in the third paragraph, because any essayist's first impulse on hearing that the best essay couldn't be about x would be to try to write it. But if most questions yield good essays, only some yield great ones."
I amusingly reject a ton of the lead in. Though, my rejection starts with the idea that there is a conceivable total ordering of essays. Heck, for that matter, I question if there is even a stable ordering of essays in a topic. Seems that what helps make an essay good for today may not be what lets it be a good essay for tomorrow.
And that isn't even getting into things like "must tell you something you didn't know." By that, I can never find an essay that I've read before to be great? Or to learn from one I have already read before, but from a different perspective?
Will be fun to read more of what others hear in this essay. I suspect I should give more credence to the idea of the best essay for today. And each day can be another search for today's winning entry.
“While breadth comes from reading and talking and seeing, depth comes from doing. The way to really learn about some domain is to have to solve problems in it”
Much of the restricted depth of this nature is a consequence of deliberate obfuscation or neglect by the people who are involved in the doing, such as trade secrets, or simply choosing not to write about or share the actual things that impact their craft.
You can easily accumulate depth of knowledge from reading in areas that are well documented.
How can you claim your knowledge of the field is actually deep, if you’ve never even done anything with it? Knowledge without application is nothing, imo.
True “depth” comes from the know-how acquired in digging through all the minutia nobody else though to document, on your way to producing a new creation nobody else thought to build.
While I think there's some truth to yours and some of the sibling comments here, I think a lot of the discourse around documentation is actually just motivated reasoning.
The trope that software projects are poorly documented is so pervasive as to be saying nothing at this point. Despite extremely useful and celebrated documentation projects (MDN and Python off the top of my head) that dramatically accelerate other peoples' learning and productivity.
But when the topic is raised, the response is always "But we don't have time for documentation".
And when that time is given it becomes "It will be useless or out of date soon anyway, just go read the code" (As if there is nothing between non-practical high-level docs and per-line code comments.)
And when forced it becomes "Fine, but it won't be any good" or "Other people won't read/benefit from it anyway".
And when it's done, often as little effort as possible is put into it.
All of which smell to me like cover stories for: "I just don't want to do it."
In the case of Python, I do think the approachability of the documentation slipped after they migrated to the 3.x site, and I think this is somewhat reflected in the search engine rankings.
Henry Heimlich used "the heimlich maneuver" for the first time when he was 96 (in 2016), 40 years after inventing it, in the "senior home" where he was staying. But according to you, having invented was nothing in the first 40 years, because he didn't actually use it, never mind that it was used by others and taught as a life saving technique.
You're just beathtakingly ignorant of how progress actually happens. It's like your understanding of the world comes exclusively from thinking about the world in abstract hypotheticals, rather than interacting with it, which is ironic coming from someone stating that only action matters.
You’re so caught up in insulting me, you never stopped to think of I’d consider inventing a novel medical technique an “application” of knowledge. I would.
If all he did was read books about things other people did, he certainly would not have invented that.
Your following attempt at armchair psychology is humorous, but not much beyond that I’m afraid. Don’t quit your dayjob.
Well I certainly hope your patients can find the help they need. But let’s drop the hominems and get to the point:
Do you have a real counter example? Someone that through reading the material of others alone, with no practical/“hands on” experience, was able to develop what you consider “deep” knowledge?
Ha, I had thought you were an LLM prompted to be a contrarian with a chip on their shoulder. This all but confirms it^. I bet you don’t even have the prior messages in your context window.
^Or at least something with approximately that level of intellectual capacity/honesty.
>You can easily accumulate depth of knowledge from reading in areas that are well documented.
Given that specific knowledge relevant to a field may be of a highly specific and hard to understand nature it increases the risk that any attempt to understand that knowledge by simply reading it will fail due to simple misunderstanding of what one reads.
In documenting things there are always points in which documenting minute details of a thing starts to detract from the purpose of documentation, that is to say the more in depth and detailed one documents the less readable the documentation becomes, therefore one leaves out things that should be easily understood by others when trying to use the documentation to actually work in the field or will quickly be imparted by other practitioners in the field if it is one with easy access to others.
Documentation by its nature is aimed at everyone, but there may be particular things that would be obvious to many people but not some specific person, and that specific person when reading the best documented guides to the area of knowledge will still not be as knowledgeable as they believe, because everybody is different.
Very many areas of knowledge have specific relation to things that people do with their bodies, martial arts, sex, cooking, etc. etc. In such cases there is of course muscle memory, thus no matter how precise and painstaking the documentation will be in these areas you will not be as knowledgeable as one that builds up muscle memory in the field by doing if you rely on only reading the documentation.
I could go on, but given my point about minute details it might be self-defeating.
The default action for an autonomous entity or system is to do nothing. It’s really odd to phrase doing nothing as a choice. Anything other than doing nothing is a choice. Especially when it comes to work, most humans just don’t want to bother spending time thinking about work outside of paid work time.
I'm so tired of (mostly boomers) talking about learning how to work on cars like it's easy. Sorry guys, but the companies who make those DIY repair manuals that you guys keep talking about using to learn wrenching don't seem to make stuff for any modern vehicles. Don't believe me? Go check out how pathetic their selection is right now: https://haynes.com/en-us/
It is nigh impossible for a non-car person to learn how to wrench without direct literal hand-holding from those who do.
It's also lead to the mechanic industry being FAMOUS for scamming grandmas, mothers, US soldiers, and other captive audiences. I think the only groups with a worse reputation are lawyers and car salespeople.
Nope, most of the stuff I want to do on my 2017 RX do NOT have videos on YouTube. Good luck changing the spark plugs yourself including with YouTube. The back 3 will be impossible
It's impossible to learn to work on modern cars without help, and the idea that things are similar enough from the old cars that it carries over to modern cars is simply not true for a whole lot of vehicles. You really do need videos for each and every vehicle.
Watch even experienced mechanics works on new cars. They tend to bumble around for awhile.
There isn’t a need to read anything beyond introductory materials to acquire depth, if your competent enough.
In fact that’s what I would consider the critical dividing line between a regular genius and a bonafide super-genius. Someone who almost supernaturally acquires expertise/intuition/depth/etc. with very little visible effort.
In my experience, this is more of a fictional trope than a reality.
There aren't any Tony Starks who become experts in thermonuclear astrophysics overnight.
Richard Feynman was as close to this trope as you can get in reality, but insisted that his reputation for being able to solve difficult problems was due to having a "different box of tools" than others. And he obtained that by studying rather obsessively, well beyond assigned texts.
I have been lucky enough to know a few people who also might qualify as geniuses able to produce miraculous results. One of them decorated his laptop with the logos of defunct computer companies of the 1950s-1980s. He drew a lot of inspiration from papers and books that few others have read in thirty years.
I’d assert that, rather than being fictional, it’s just exceedingly rare. While Feynman, Einstein, von Neumann, et. al. are indisputably geniuses, they all got relevant graduate degrees before doing their best work. The self-taught Indian mathematician Srinivasa Ramanujan, however, was invited to Cambridge University on the merits of notebooks he developed in isolation after reading a few mathematical texts…
The original claim was not that geniuses and savants exist. They clearly do!
The original claim was that a genius should be able to easily and quickly attain mastery of any topic, given a grounding in the basics. Like, you give Mr. Super Genius IQ a book on quantum chemistry and the next day they’re putting things together so cleverly they are on the precipice of new discoveries.
Feynman actually did this a couple of times! But I think that just shows the “unreasonable usefulness” of mathematics, as well as his own spirit of curiosity. (And at least one time that we know of, he faked it by reading a colleague’s research before he presented it. Not to take credit, but just as a prank, so he could interrupt and predict every conclusion before the presenter finished.)
Ramanujan is particularly interesting because he repeatedly claimed that divinity gave him his results.
I'm an atheist but when someone like him tells me that god gave him all of his equations - I'm not going to respond with "well ackshully". I'm going to ask them how we can make it easier for them to listen to god.
Story from a friend who once was offered the first PhD in Computer Science.
He once mentored a guy who was so ridiculously good at writing programs, that he wrote out (once) a 5 foot stack of punch cards (back when that was how you would code), to create a program that was needed by the company for some purpose.
It worked, flawlessly, the FIRST time.
This was his MO.
Once, he wrote a program for an internal client, and it got shipped. They ran the program and ran into a problem. My friend told him to debug it for them… he replied “I don’t know how”. Up to that point in his life, He had never had to debug a single piece of software…
My friend helped him debug the program: Turns out, the problem was not an issue with his code, the customer had given him the wrong spec for a critical interface… and that was the only reason it had not worked the first time.
There are truly people that qualify. The only note I will make is that generally if you are a super genius in one dimension, you likely have something you are absolutely terrible at in another. Hopefully it is in a dimension that either doesn’t matter, or you have enough complementary people around you to mitigate it.
I don't buy it. Every supposed super genius I ever heard about in the end had a tactic to their work. Even the high iq people have to have an approach to harness the intelligence.
This was 30+ years ago… I don’t know the details, but trust the source. The source used to teach at Carnegie Mellon. The point my friend made to me was that this guy was so good he never had to debug a program after he was done.
FWIW, apparently back before Intel released a particular 4 bit processor, this guy made an emulator and compiler for the chip so they could start writing code in anticipation of its release.
Once again, not direct experience… but trusted source.
lol, yes… it is indeed fun to share these stories.
Two alternate stories I didn’t tell:
First is about my two friends (both ridiculously smart) who in undergrad became the TAs for the Operating System class at Carnegie Mellon as undergrads (normally taught by grad students)… this is the hardest CS course taught there. As part of their summer prep, they wrote a new file system example… I believe based on a b-tree.
The next was my AI professor, Andrew Moore [0], he was legendary at the school… eventually becoming dean after doing a stint at Google (he has since stepped down). By far, he is the smartest person I have ever personally known. To give you context (and we did this regularly in his class), you could ask him a question on anything and he would pause, think about it, and come up with a well reasoned answer that would be both insightful and illuminating… from first principles. On any subject. You could not throw him (we tried). I am still in awe of him.
While I agree that legendary tales grow… they are almost always based on a kernel of truth. The reality is most people don’t often interact with folks at these levels. I was very lucky, and I have only interacted with a handful.
What you're describing as a "super-genuis" is just someone that thinks they know it all after reading some introductionary material. They don't know what they don't know so they think they're "done".
Take this how you will but in my mind most of them are intellectual yet idiots. Little empathy and no social awareness. They may be technically smarter than their peers but so what?
These are the kind of people that would probably create weapons of mass destruction and if you might discuss with them with the scale of destruction of their products they have nothing to offer yet they will giddily discuss the technical achievements of their projects.
there are people out there who are better than you in every single regard. dont be jealous, be happy that the world can be composed of people better than you dreamed
What a bold conclusion. I remind you that you don’t know anything about me. But perhaps your characterization is to protect the comfort you draw from your world views.
What kind of person thinks that the people whose “brilliance” led them to invent weapons of mass destruction are better than anyone that cannot solve technical problems as fast as they can? Do you apply the same reasoning for wealth also? I suppose might is right for you?
You might not see this — for whatever reason — but it is indisputable: history is filled with the types of “geniuses” who in their rush to the prestige of being first they leave in their wake destructive effects on humanity. I argue that when people say “these are 1 in a hundred million” that yeah, because most of the people with similar aptitudes would pause and consider the implications of their actions while you argue that they are gods amongst men that we are “lucky to have met”.
> I remind you that you don’t know anything about me.
Yet you are willing to cast ridiculous assertions about groups of people - stating as fact as though you are the canonical source of truth.
> But perhaps your characterization is to protect the comfort you draw from your world views.
Seems like you define projection.
See if you can find a way to get a colleague or two to tell you what they honestly think of you. I'm sure you will be surprised at how they judge you. The trouble is getting honest feedback - people say they want it but few people receive it well so over time most people learn not to give their opinions.
Do you think the world will be better off if, let’s say, all these powerful super geniuses dedicated 5% of their time to deeply consider questions like “should I be building this” or “should I be working for this corporation”? With the same enthusiasm and rigor that they dedicate to their craft.
If you don’t see how many of these types are so immersed in their craft that they are oblivious to their impact on the world then you really haven’t interacted with many high-functioning types. If you have I encourage you to try and discuss these types of things with them.
Have you ever seen the tv news or read the newspaper when they cover a topic related to what you do for a living? Or a specific event you were a part of organizing? They usually have interviews with the “experts” you’re talking about. How do you feel about their accuracy and experience?
I misread that for a second as "while breath comes from reading and talking and seeing, death comes from doing" which I thought would be a great line from a Zorro film, even if not that sensible.
I think the concept of a best essay is somewhat illogical, but exploring the idea like this makes an interesting post.
After all, the term "essay" was invented/popularized by Montaigne in a book of his writing called "Essays" - and "essay" is French for "to try." So from that context, essays shouldn't be concerned with finding answers or be the "best" but to make discoveries in the process of trying.
From that same Wiki definition I notice that "In English, essay first
meant a trial or an attempt.
That implies an iteration on some seed, or maybe just the intent to
grow and iterate on the initial essay.
Personally I find that true. Most of my "essays" I keep for myself, or
sometimes share just with close friends who I trust to bounce ideas
off as they mature.
Later they become collections of essays in a folder, and I might join
the dots between them to perhaps see the potential for something of a
book, or a new essay that synthesises them.
So I think calling something an "essay" grants the author one special
privilege; the right to revise and "re-attempt" the same piece without
moral judgement.
That's problematic in the Internet age, where the provenance of a
document is judged by dates, by diffs to archived versions etc. It
wouldn't seem right to actually change the contents at the same URL.
Nor would it seem right to insist on tracking edits, because a writer
always has the right to forget and disown old and weak ideas they've
moved beyond.
So I think essayists have our permission to keep approaching the same
idea over and over. The way composers would sometimes write ten
different versions of the same piece.
What makes a "best" essay then is its improvement with respect to the
author's previous attempts.
All we can ask is, "Is this Mr Graham's best essay so far?"
In Spanish we have ensayo = attempt or try, frequently is used to refer to attempts before the real show or performance (in a music festival, a theater, ..). Also ensayo is just equivalent to what Montaigned introduced when referred to a text composition.
That site doesn't seem great, but according to Wiktionary "assay" is a doublet of "essay", i.e. the origin is the same but they were borrowed into English via two different sources.
"Assay" came via Norman, "essay" came via French.
There are lots of other examples like this where one word came from Norman and the other from French, e.g. warden + guardian, warranty + guarantee
Good comment. It surprised me that a definition of essay wasn't sought before asking questions about the supposed best. But that tentative approach actually struck the essence in an interestingly performative manner.
> I think the concept of a best essay is somewhat illogical, but exploring the idea like this makes an interesting post.
pg does specifically address this objection btw:
> I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three. This essay is an example. Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
> Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
Preemptive dismissal of any criticism of the idea of a best essay is stupid. In particular, even though I buy the "possibility of one essay being better than another", the criteria for ordering will be necessarily subjective.
As someone who has read many essays in the European tradition (Montaigne, Sartre, etc.), I cannot bring myself to see the essays by E. B. White, for example, to be superior in any sense. Yet, I know that White's essays are held in high-regard in this part of the world. This points to the fact that there is no universal ordering function for essays, which mostly invalidates Graham's argument above.
What a strange essay! To try to find out what makes a good (sorry "THE BEST") essay without any reference to any of the great essays that have actually been written? It feels a bit like the head of a university's English department setting out to discover "the best computer program" but without talking to or refering to the work of any of the thousands of people who've made it their life to study and practice the craft.
> For example, Darwin first described the idea of natural selection in an essay written in 1844. [1] Talk about an important topic you could tell people something surprising about. If that's the test of a great essay, this was surely the best one written in 1844.
I think he's speaking broadly about what counts as an essay, and does have at least one example in there to illustrate his point. He's also an esteemed essay writer, and I think it's fair for him to talk about what he values in an essay without needing to justify any of it by saying "and also, this person that some people respect did it like that"
Most of the time so, this approach leads to very deep discoveries of the kind other people learned in the first days of a 101 lesson studying said subject, at university or during some formal training of trade or craft.
IMHO, the best [individual] essay contains single paragraph/sentenced trasmissions that connect [or overhelm] the reader with impact at [the right] times.
At the same time, to strengthen the practice, make a statement and then follow with a question. Make the impact, leave the reader with a question back to it. It's two sentences, paragraph break.
Those are the best essays.
He practiced this technique many times in this article. But is this the format of best essays [of the Internet]?
I'm struck by the parallelism between this process of writing the best essay, and the process of developing a successful startup. Both require starting with a good question, that sets the upper bound for the value to be created. Both require curiosity, and hopefully to reveal some unintuitive insight. Both are functions of their time, what is a good startup today is not timeless much as what makes a good essay today is not timeless. And so on...
> It probably wouldn't be about this year's lipstick colors.
Women are so superficial (cringe)
This essay reads as if someone has too much time on their hands and is so self-absorbed that you get blog post titles like this and my god what on earth did I actually read?
Interesting to see Sam Altman thanked. It's the first time since July 2020, 29 essays ago, and this is also Graham's first essay since the hullabaloo at OpenAI.
I wondered that too. A subtle endorsement of Sama perhaps. A way of saying there's no bad blood there despite what the press was saying about his 'firing' from YC. Sama did a great job running YC, and certainly made PG a boatload of money. Also seeing the success at OpenAi, hard to argue Sama didn't make the right call to leave and focus on it, could hardly have done that plus keep running YC. (my guess at what happened is Sama started openai on the side and gradually it became more and more of his focus until there was a conversation about whether he should focus exclusively on it, which they mutually decided should happen).
PG is an inspiration for me to start writing. It’s an uncomfortable exercise to get started but I agree that clear writing makes you into a clear thinker and communicator.
> If you're willing to do a lot of rewriting, you don't have to guess right. You can follow a branch and see how it turns out, and if it isn't good enough, cut it and backtrack. I do this all the time.
I feel like even if you guess right, you can't help but do a lot of rewriting and exploration because otherwise you'll always feel that "something's missing", and that you're further from the truth than you could be, that there's a better explanation around the corner if you study this subtree a bit more.
In the process of an essay I'm currently writing, I've probably written a short book of meandering thoughts / notes. I can't imagine it any other way because doing so would be imagining me actively not exploring an interesting subtree / implication of something I wrote, that I feel could impact the crux of the essay.
And of course none of this is wasted effort, as PG talks also mentions. Identifying the next essays from those ideas I've left out of this one is simply an act of observation and organization based on the exploration I've already done.
And likely when I start the next essay, this process will repeat itself.
Right now using Obsidian (without being good about connecting notes). I'm just writing, dumping into a folder, and leaving further organization / analysis for later.
> Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
Not to be a pseudo-intellectual, but this confuses partial orderings and total orderings. It makes for a fun discussion, but I hope Paul would agree that there's obviously no "best essay", real or hypothetical.
Not to mention that "best" is subjective, so there is no single ordering, but "How to write Paul Graham's favourite essay" wouldn't get as many clicks on HN (ironic for a site with anti-clickbait rules).
In earlier drafts I wrote "the existence of some set of best
essays follows necessarily" but it sounded so pedantic that it didn't seem worth keeping just to protect myself from being accused of not understanding the distinction between a partial and total order. I assumed anyone reading it in good faith would understand what I was saying.
Seems to me something like songwriters in popular music. Proven hitmakers and their expert associates still can't say for sure which of their offerings will resonate like nothing before.
You always have to try or you wouldn't have a chance. But you can't just sit down and determinedly write your best material ever, with any kind of certainty, right when you decide to.
Paul has been putting me off lately. Everyone that disagrees with him is a "pseudo-intellectual" or some other hinted-at bad or incomplete person. The guy loves the smell of his own farts and isn't the towering intellectual or writer than he congratulates himself as.
I found your comment by searching for "it follows necessarily from the possibility of one essay being better than another" because it stood out as a fallacy.
Not surprised that pg proves once again that he is little more than a narrow-minded capitalist, who doesn't actually understand anything about culture, the humanities, literature, or what it is people actually value in those spaces.
His writing is consistently flat, uninspired, and egotistical. He's ok at writing clear prose and this plus his success in relation to YC has made him popular among technical people that also embrace capitalism. Anyone outside of this little cult realizes that pg says very little of value, particularly when he decides to comment on subjects outside of his capitalistic and technical wheelhouses. I have not read a single pg essay that touches on culture, ethics, or general epistemology that has given me anything other than a complete groan of a reaction and astonishment that this is the sort of thinking that passes the "high-quality" bar for the average technologist.
pg can try as hard as he can to write the "best essay". He will never convince this reader since he occupies a completely different world and basically isn't even capable of speaking to this audience in the first place.
...just to lengthen this comment more than is due, the quote is astonishing. I mean, how arrogant do you have to be to claim that the past hundreds of years of literary development, in which the notion of "best essay" is considered at best completely relative and at worst nonsense, must be wrong and that anyone who thinks otherwise must just be a "pseudo intellectual" (read: someone who disagrees with paul graham). He's really high on his own supply.
I often think about this as a sort of counterargument for rationalism. Or maybe it's more of a paradox than a counterargument:
Suppose you were trying to answer the question: "what is the best way to make as much as money as possible in the next year?" You imagine optimizing yourself or your company or your algorithm or whatever to answer this question. Maybe it does a bunch of calculations and decides the answer is "day-trading commodities futures" or something. Or maybe a company does this and thinks the answer is "spin up a new product and sell it". (Or any situation where you're optimizing some other variable, like "altruism" or "security".)
Well, in almost every case, some of the best answers are "do something impossible". For instance, "write a story that is so good you get a 1 billion dollar book deal out of it". Or "write an essay that convinces everyone to give you all their money". Or "hack something that's considered unhackable and take all the money". What if the most altruistic thing you can do is... convince everyone to become pacifist? Or start a new religion? Etc.
Each of these has the property that rationality alone can't really model it. An algorithm can't analyze reality and say "write a story that is so good you get a 1 billion dollar book deal", or "write an essay that convinces everyone to become pacifist". (Maybe an actually-sentient AI can. But that's about it.) The only way you could come up with that as an actual strategy is to have an unrealistic belief that it is possible. Basically to have faith in yourself and your vision of the world despite the evidence for that strategy not being solid.
Yet the strategy can work. History shows that sometimes it does. And for a particular person at a particular time it might be the right answer. But it will never be the "right strategy" according to an outside computation.
I dunno. Always felt like that was interesting. Not sure if there's a word for it. If not I would call it the "miracle paradox": miracles occur, but you can't rationally justify them as a strategy, yet believing you can pull one off is necessary for them to happen, in which case they are the correct strategy.
I feel like the missing ingredients are risk, variance, cost, time horizon etc.
"Moonshot" type endeavours are not paradoxes. They do involve considerable uncertainty and usually some kind of large investment (time, money or something else). Most can't afford them and don't have any particular reason to believe they will be more successful than everyone else who has tried. Relative to most people's resources, time preference and risk tolerance they are bad bets.
If you are starving then your strategy for getting food should usually be the one with the highest overall chance of success, you care much less about factors like effort/reward ratio or getting the highest possible payoff.
The most common strategy for people who want a tiny chance at an enormous payoff is to buy a lottery ticket. Millions of people do that every week.
Such bets absolutely do feel paradoxical at times because multiplying a very small chance of success times a huge (usually easier to reason about) payoff seems to break people's brains a bit. This is often described as a "bug" in human cognition, though I have always felt it's an instinct for "exploration" in the sense of occasionally making small bets with huge potential payoff "just in case" your world model is wrong. Also that the way humans process probabilities and payoffs seems more logarithmic than linear (making small probabilities "feel" bigger than they really are).
This response represents some confusion on your part and not a paradox or counterargument to rationality.
very very roughly the ideas you need are:
1. survivorship bias
2. self-interested optimisation is not guaranteed to lead to a global maxima, e.g. self-interested agents may be systematically less risk-taking than would be societally optimal.
3. it's fine for rational agents to account for private information, e.g. "I did really well at Stanford probably I have a better shot at a company than a random person." is a fine thing to include in reasoning.
I disagree that it is confusion on my part (I mean, I am certainly confused, but not, I think, about what you said). Your (1) and (2) seem irrelevant since I am talking about the personal EV calculations of individual actors, not global EV. (3) is the point I am trying to handwavingly describe a way of skirting. But it sounds like I didn't communicate it well (or I am wrong about not being confused also, in which case, fine, can't do anything else anyway).
Yes, of course rational agents can account for private information. I am trying to describe a case where a strategy cannot be rationally justified, yet is a better strategy than others because of "having faith in yourself". Now you can always try to flip this around and say: "well maybe the internal calculation that they do involves having evidence that they ought to have faith in themselves, like past success, consistently good mental models, a model of how faith helps, etc". And I'm not talking about those: I'm talking about cases where there is not a good argument, even in an internal calculation using private information, why a person should have faith in themselves, yet doing so anyway helps.
Basically it seems like there are cases where believing that something has a more-than-rational chance of working makes it more likely to work because of the power that irrational faith in yourself provides. But suppose you tried to quantify it: okay, an irrational faith in yourself makes you, I don't know, 20% more like to succeed, so you can account for that. But now it's not an irrational faith, it's a rational one, so you can still have more irrational faith than that, and it can still have the same effect.
My pattern-matching brain says it has the form of a Halting Problem/Godel-incompleteness-type theorem for rational calculation. Roughly: "It is possible to construct scenarios in which non-rational strategies lead to improved success in ways that rational calculations cannot account for."
This would not apply in a toy problem where the range of strategies are completely mathematically known: if all outcomes can be understood probabilistically then it doesn't apply. It applies in cases that are more like: some outcomes are unknown and the probability distributions of them are shielded behind "unknowable information", like new ideas that you have no way of being sure of the existence of. In these cases an irrational belief that you can find a new idea can improve your EV even though there is mathematically no way to justify it, because you can't really model "the probability of finding a new idea" without actually knowing what the idea is, even hypothetically.
I had a tangential insight recently. Your "best" isn't actually all you can do, because your idea of what your best is, is limited by your self-concept. Similarly, it is possible to do some things that are widely considered impossible.
From this it seems that the best strategy for doing impossible things is to assume that impossible things are actually possible. It's only by doing that that you'll find out.
It's a risky strategy though, since many things are actually impossible, and even for possible things, they may be difficult, or the easy way may be hard to discover.
Maybe there's some hueristic for sorting the actually possible, and from there, for sorting the reasonably doable.
But I'd be wary of hueristics because (barring unusual personal experience) they're likely to suffer from the same bias that led people to dismiss things as impossible in the first place.
me: write a story that is so good you get a 1 billion dollar book deal
Claude 3 Opus:
Here is a story that I hope captures your interest and imagination:
The Memory Thief
In a world where memories could be extracted, bought and sold, Lina was the most skilled Memory Thief in the business. The wealthy elite paid handsomely for the chance to acquire the experiences and skills of others. And Lina had no qualms about stealing memories from the unwitting. It was just business.
Her latest mark was Jonathan Thorn, a reclusive tech billionaire. The bounty on his memories was the biggest Lina had ever seen. Enough to set her up for life.
Infiltrating Thorn's mind was surprisingly easy. But as she slipped into his memories, Lina found herself drawn in by the raw beauty and staggering brilliance she discovered there. She witnessed Thorn's greatest triumphs and his deepest heartbreaks. And she began to question everything about her life as a thief.
Then, in the innermost recesses of Thorn's mind, Lina uncovered a memory unlike any she had ever encountered - a memory of the future. In it, she saw a world in flames, its population enslaved by a ruthless dictator. And she saw herself and Thorn, leading the last desperate resistance against the tyrant's armies.
Shaken to her core, Lina fled Thorn's mind without the bounty memories. But she took something else with her - a newfound resolve and a dangerous knowledge.
Now, Lina must track down Thorn in the real world and convince him that his prophetic memory is true. Together, they must figure out how to prevent the apocalyptic future only they know is coming.
Even if it means Lina must do the one thing a Memory Thief is never supposed to do - reveal who she really is.
What follows is a race against time and a battle against fate as an unlikely pair - the world's most notorious thief and the man whose mind she invaded - become the only hope for salvation. All the while, a forbidden love blossoms between them, forged by the intimate knowledge of each other's deepest secrets and the heavy burden they now share.
In the end, they will have to sacrifice everything to rewrite the future. But in the process, they might just find that the most valuable memories are the ones you make with someone else.
My God, this is truly beautiful. If this were the blurb of an actual novel, I would unhesitatingly drop EVERYTHING to read it, and I say this as someone who reads an average of 1 novel every 3 days.
> The best possible essay at any given time would usually be one describing the most important scientific or technological discovery
To a hammer, everything is a nail. I love technology and science, but that doesn't mean that is what makes the best essay. Relationships are key to our survival, so I suggest personal relations could be just as good an essay as anything scientific - yes, I'm suggesting that social science isn't really a science.
This also then leads to timelessness. The essay on natural selection is timeless. It wouldn't be written today, but it is still a viewport into the discovery, and of the time, and the knowledge is still valid. Maybe I am misunderstanding the point about timelessness.
> The other reason the initial question matters is that you usually feel somewhat obliged to stick to it.
I also disagree with this comment. I'm currently writing a talk I've been asked to present, and in the process of my writing and researching, I've discovered a whole new and better question. I find the point of a good question is that it can lead to better questions. I do feel that PG is suggesting this as well, but maybe this one sentence just stuck out to me.
> I'm suggesting that social science isn't really a science.
In reality and practice, no effort at science is 100% "really a science".
But for "social science":
(1) It can be a goal to have some of social science be real science.
(2) My wife's Ph.D. was in social science, and her dissertation was real science. The work started with a real question, in social science, gathered some real data, analyzed the data statistically, and came to some real conclusions. The conclusions were "new, correct, and significant". Some science? Yup.
>The best possible essay at any given time would usually be one describing the most important scientific or technological discovery
That sounds like a trekie concluding that the best literature is "Star Trek" licensed novels...
Sorry, but PG didn't invent or define the essay.
It is a form that is centuries old (and in prior incarnations, millenia old) and have its own long cultural history, classics, and canon, few of the latter being about "important scientific or technological discoveries".
Maybe if instead of "best" he changed it to "most impactful scientifically" he'd have a point.
I graded a lot of humanities papers in a previous career. One of the weirder genres of bad paper would come from very smart computer science/math/physics majors who didn’t have time to do any of the assigned reading and just kind of tried to answer the prompt from first principles without citing any primary sources or other scholarship.
This feels like that paper, except the author isn’t a stressed-out college sophomore but a 59 year old “thought leader” with a large audience who gets Sam Altman to read his drafts. No attempt to engage with the history of the genre at all, or with the many other writers who have considered the form, and no examples cited except a famous scientific article by Darwin.
I never saw this essay before. Thank you to share. A choice quote:
> I blame Eric Raymond and to a lesser extent Dave Winer for bringing this kind of schlock writing onto the Internet. Raymond is the original perpetrator of the "what is a hacker?" essay, in which you quickly begin to understand that a hacker is someone who resembles Eric Raymond.
> The whole genre reminds me of the the wooly business books one comes across at airports ("Management secrets of Gengis Khan", the "Lexus and the Olive Tree") that milk a bad analogy for two hundred pages to arrive at the conclusion that people just like the author are pretty great.
Definitely a fun read, but the author has an axe to grind with the references to "who gets bitches" and the unnecessary footnotes. Take what you will from it.
There's no literal quote about "who gets bitches" or the word bitch at all in the post though. What you refer to is a paragraph about the distinction between programming and painting (meant as a joke counter-argument to PG's essay about how hacking is essentially like painting), which opens like: "Great paintings, for example, get you laid in a way that great computer programs never do".
The author (who is on HN, btw, too) does go into a more substantial difference of the nature of the two endeavours too, but the whole post is in a jocking tone. And yes, it has "an axe to grind", but it's not about who gets the girl. It's about taking down essays they consider pompous and self-congratulatory.
> Relationships are key to our survival, so I suggest personal relations could be just as good an essay as anything scientific
Some of my favorite books are old literature that describe relationship dynamics I still see playing out between people today. Swann’s Way, The Brothers Karamazov, even Canterbury Tales…
I think it was Vonnegut that wrote that the best books are the ones that tell you what you already know [but maybe you didn’t know you knew till you read it]. That’s something like surprise, and yet something like the opposite.
I enjoy helping others to think outside the box. You have done quite well in placing your own perception onto two dimensional paper. Thanks for inspiring my own out-of-box interpretations.
The hardest part of writing is it's hard to predict how it will be received. You cannot 'focus group' writing, unlike other mediums of information.
Disney can predict with a high degree of certainty that its superhero movies will do well, as there is a large, built-in market for those movies, and they tend to be conceived on the same creative blueprint or foundation. Even its 'duds' are still profitable.
But this is not possible with writing, especially not internet writing. What is the market for short-form contrarian non-fiction? Who knows. It's hit or miss, mostly miss
> Disney can predict with a high degree of certainty that its superhero movies will do well, as there is a large, built-in market for those movies, and they tend to be conceived on the same creative blueprint or foundation. Even its 'duds' are still profitable.
Google something like "Marvel superhero fatigue". It seems that either the movie quality is decreasing or the audience is becoming more and more bored by these movies.
Is it important to predict how it will be received? If you are trying to tailor your work for your audience, then you are on your way to being yet another content farm and when’s the last time any of those published something great?
I know Paul does have some trusted readers that he shares early drafts with. Maybe he uses those readers as his focus group?
> One thing I like in an initial question is outrageousness. I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three.
I believe it is possible/likely that the best essay in the world could not be realized as such (thus, it wouldn't/couldn't be the best essay in the world), because most people couldn't even get by one of these let alone all three...and, there's likely to be many other hurdles one would have to make it over.
Yeah. Imagine writing Darwin's essay on evolution in the 15th century. People wouldn't have been merely outraged, they would have killed him right away. And also today some possible essays may contain true and important insights, while being too taboo to not be immediately dismissed by society.
It is not enough to ask novel questions. Trick is to ask questions that do not offend the delicate sensibilities of the overlords of public discourse.
This has been a challenge since time immemorial. Darwin was not exactly feted then.
Maybe at the limit the best essay becomes a poem: a beautiful piece of writing that explores interesting ideas, yet always leaves room for new and different interpretations, even by the same reader.
There's a fantastic series of podcasts on great essays by David Runciman from the London Review of Books, which aren't always the ones you'd expect given the authors:
Q. How well--perhaps on a scale of 1 to 10--does this essay follow its own recommendations? Is it a great essay by its own standards?
A. The essay "The Best Essay" does follow many of its own recommendations, but it also falls short in a few areas. Let's evaluate the essay based on the 10 rules it sets out for writing great essays.
Important topic with surprising insights: 8/10. The topic of what makes a great essay is important for writers, and the author provides some surprising insights, such as the idea that the best essay would be about a groundbreaking scientific or technological discovery.
Compelling question: 7/10. The essay starts with the question of what the best essay would be like, which is interesting but not as compelling as it could be.
Thinking out loud and refining: 9/10. The author does an excellent job of thinking out loud and refining their ideas throughout the essay.
Recursive process: 8/10. The essay follows a recursive process, with responses generating further questions and exploration.
Cutting content: 6/10. While the author mentions cutting a 17-paragraph subtree, it's unclear how much unnecessary content remains in the essay.
Following novelty and generality: 7/10. The essay explores novel ideas but could have delved deeper into some of the more interesting tangents.
Writing about interesting topics: 9/10. The author is clearly interested in the topic of essay writing and what makes essays great.
Breadth and depth of knowledge: 8/10. The author demonstrates a broad knowledge of essay writing and related topics, but the depth could be further developed in some areas.
Aiming for timelessness: 7/10. The essay discusses the concept of timelessness but doesn't fully achieve it, as some of the ideas may not be surprising to readers well-versed in essay writing.
Discovering ideas through questions and answers: 8/10. The essay does explore ideas through asking questions and refining answers, but the most valuable questions could have been pursued further.
Overall, the essay scores well in following its own advice, with an average score of around 7.7/10. However, it falls short of being a truly great essay by its own standards. The author could have pushed further in exploring the most compelling questions, cutting unnecessary content, and aiming for more timeless insights. Nonetheless, it remains a thought-provoking and insightful piece on the art of essay writing.
Is it overly reductionist to wonder whether the difference between, “Which of these is best?” versus “Is that your best effort?”, deserves more than a footnote?
> If caring about it is one of the criteria for a good initial
question, then the optimal question varies from person to person.
with another submission posted some 15 minutes later [0] noting
J. R. Ackerley’s ability to make anything compelling through the sheer
weight of care
The "best essay" for an author is certainly cantered on their care.
Yet I feel in the current nonchalant, urbane and cynical climate if
the audience sense any sniff of "care", it is to be savaged.
Unless it tickles something sentimental or ironic, care is despised
and dismissed as weakness that "doesn't make a living" or is some
wonky "ideology".
But then people would call me cynical for saying that :)
"One thing I like in an initial question is outrageousness. I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three. This essay is an example. Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another. And thinking about how to do something so ambitious is close enough to doing it that it holds your attention."
> Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
What is the best car? Some cars are real stinkers. It's not hard to find cars that are better than Zastava Yugo in every way. For most cars you can find other cars that are in the same class, but just better. Clearly, a comparison between cars can be made. Car reviewers make this their job.
But from the existence of bad and mediocre cars it doesn't follow that there is such a thing as a "best car". How large is your family? Do you want to tow a boat? Do you like to go fast on curvy roads? Do you care more about acceleration or range? How tall are your rear passengers?
There are good essays and there are bad essays. Some essays, perhaps, can be considered the very best in their category. But you can't rank order essays across categories, just like you can't argue that a Ford F150 is objectively better or worse than a Mazda Miata.
(And if this makes me a small-minded pseudo-intellectual so be it.)
you can't argue that a Ford F150 is objectively better
Perhaps if you limit yourself to a hidebound traditionalist view of the form but this topic has been explored by the Moving Picture Essay https://www.youtube.com/watch?v=oMDcIApBtL8
This struck me too. I think we can do better than appeal to insult. Especially given the potential technical mistake. It’s quite disappointing, in a way.
This sounds like how I would write when I was on adderall. I mean, what the hell is this statement?
"I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three. This essay is an example. Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another."
That's not what "follows necessarily" means Mr. Graham. Are these pseudo-intellectual spectres literally just you strawmanning your own counterfactual? I can't imagine you actually listening to anyone you would call a pseudo-intellectual.
That quote is also just factually wrong because we can have partial orders, or even just have a lot of totally different essays that happen to be equally good.
I admired Paul Graham's blog posts.. when I was an impressionable college sophomore.
Then I guess after I went to grad school and actually read a lot and tried to do some science and research. I find this kind of popular writing superficial, flawed, inefficient, and even conceited. That's just my subjective experience. But it seems some young people in tech just lap it up, he functions as a kind of thought leader for the industry.
I think if you've ever read self help books, the content is quite similar. It is the kind of writing that seems insightful at first glance because it restates somewhat obvious things in new ways.
I'm not saying that his arguments are 'wrong' persay, it's just that it's not particularly original or interesting.
>It is the kind of writing that seems insightful at first glance because it restates somewhat obvious things in new ways. I'm not saying that his arguments are 'wrong' persay, it's just that it's not particularly original or interesting.
You're spot on. Looking to this very comment section, you have people calling this line out as being enlightening:
>While breadth comes from reading and talking and seeing, depth comes from doing.
I would hope this is self evident to anyone who has ever tried _anything_.
I find the separation between the body of the essay and notes makes it harder to read. When I read PG's essay, I always have two tabs open, one on the essay and the other on the Notes section. When I come across a note reference, e.g. "the answer turns out to be completely different. [4]", I switch to the Notes tab to look it up. This back and forth between the two tabs disrupt the reading experience.
Wouldn't it be easier on the reader to simply include the Notes in the body part of the essay? Especially when the notes are short. For example the aforementioned note no. 4 goes:
"[4]Corollary: If you're not intellectually honest, your writing won't just be biased, but also boring, because you'll miss all the ideas you'd have discovered if you pushed for the truth."
Which is short, relevant, and insightful. What's the criteria for which piece of text goes into the body of the essay, and which goes to Notes? I guess if a substantial percentage of readers skip the Notes part, then it's a time-saving practice to separate the two.
You can click on [4] which brings you to the footnote and when done you can just use the back button which brings you back to [4] in the text. Works for me.
Sadly some of us (including me) have forcibly unlearned this method after discovering that too many combinations of browsers and webpages don't support this reliably.
Having to manually scroll or search back to where one was reading after clicking an intra-page link and finding out that the back button doesn't work or navigates to somewhere unexpected is just too annoying in the long run.
With books, I tend to not bother with the notes if they are bundled up at the end of the book or chapter. I prefer to have them on the bottom of the page. A web page doesn't even have the benefit of easy page turning to a bookmark, so I think some medium adapted solution like mouse hover would be appropriate.
I couldn't help but think of Nicholson Baker's first novel [0].
> The Mezzanine tells this story through the extensive use of footnotes—some of them comprising the bulk of the page—as the narrator travels through his own mind and past. The footnotes are quite detailed and sometimes diverge into multiple levels of abstraction. Near the end of the book, there is a multi-page footnote on the subject of footnotes themselves.
I agree, having them separated is quite bad. They could have just put them into brackets ( ) and include it in the normal body of the text, that way if you're not interested you can just skip it, but if you are interested then you don't have to list through/switch tabs/search at the bottom of the page/...
I believe that the reading flow is quite important, probably near the top of importance, because if the reader gets into the reading flow they're much more likely to read it all and enjoy it!
> There is, and on the face of it, it seems almost identical to the one I started with. Instead of asking what would the best essay be? I should have asked how do you write essays well? Though these seem only phrasing apart, their answers diverge. The answer to the first question, as we've seen, isn't really about essay writing. The second question forces it to be.
I'm reminded of a philosophy joke:
An angel came down for a meeting of the American Philosophical Association. Greeting the assembled philosophers, the angel offered to answer any single question for them. Immediately the philosophers set to arguing about what they should ask. So the angel said, “Alright, you figure out what you want to ask. I’ll come back tomorrow.” And he left the philosophers to deliberate.
As the philosophers argued about the best question to ask, one philosopher suggested: “What is the best question to ask?”, in the hope that some day another angel might make a similar offer, at which point they could then ask the best question. But this suggestion was rejected by those who feared that no such opportunity would arise and did not want to waste their only question.
Another philosopher suggested asking "What is the answer to the best question we could ask?" Which was roundly criticized because of the possibility that the answer would give no hint to the question it answered. One philosopher cheekily pointed out that the angel might reply "42 of course."
Finally, the philosophers agreed on the following question: “What is the ordered pair whose first member is the best question to ask, and whose second member is the answer to that question?” Satisfied with their decision, the philosophers went to bed.
The next day, they posed their question, and the angel replied: “Of course: it is the ordered pair whose first member is the question you just asked, and whose second member is the answer I am now giving.” And then he disappeared.
This is like trying to access information buried inside a data structure. You need the right incantations to get the right information content and not just the headers.
...I don't think I get it. Like, if the angel is going to be a jerk, he could be a jerk with any question.
The philosophers could have asked "What is the meaning of life?" and the angel would answer "Of course, it is the meaning of life," without any of this ordered pair nonsense.
I think it is a reference to Gödel's incompleteness theorem.
> What is the ordered pair whose first member is the best question to ask, and whose second member is the answer to that question?
Is isomorphic to:
> What is the highest cardinality set in the set of all sets?
"What is the best question in the set of all questions?" is itself "what is the best question in the set of all questions?"
"What is the highest cardinality set in the set of all sets?" is itself "the set of all sets".
"What is the answer to that question?" is an assumption of bounded size, and therefore isomorphic to saying "the largest set that is not itself."
> What is the answer to the best question we could ask?" Which was roundly criticized because of the possibility that the answer would give no hint to the question it answered. One philosopher cheekily pointed out that the angel might reply "42 of course."
42 is a valid answer because if you assume two contradictory statements are true at the same time, then all statements are true. The cheeky philosopher is pointing out that "What is the answer to the best question we could ask?" implies self reference, which implies a contradiction.
The philosophers asked a self referential question and got a self referential answer.
Good essay! Shame he doesn’t talk about taboo. Taboo subjects could make for great essays but it takes a lot of guts to write about them. Anything from collapse of your life, work, prison or death threats may ensue. Breaking taboos move society forward though. Keep an eye on “exceptions to free speech”.
Isn’t it pretty strange to write about what makes a great essay without mentioning a single actual essay except Charles Darwin’s natural selection paper from 1844?
Of course you can—plenty of comments are doing it all the time, including in this thread. What's not ok is to post cheap one-liner putdowns about anybody.
PG's essays really have two topics: the nominal topic, and that PG is really really smart.
Sometimes I get the same impressions about PG as I do about Derek Sivers' essays: sometimes they are insightful, and sometimes I think they were the inspirations for the /r/IAmVerySmart subreddit.
I wonder if this is some sort of 'The Emperor's New Clothes' situation or an elaborate piece of trolling. To me, this reads like a hallucinating LLM. Adding thanks to Sam Altman at the end sells it beautifully.
Something VC essays have in common with ChatGPT responses is that they make confident assertions in a million different subject areas without any citations at all. I was hopeful that the hyperlinks in this essay were citations to sources, but the ones that aren't links to footnotes with more opinions are links to other pages on the author's own blog.
> The best essay would be on the most important topic you could tell people something surprising about.
The premise is wrong (or at least not obviously right) IMO, so I have a hard time taking any of the rest of it seriously. Could the best essay not be the most emotionally moving? The best when heard aloud? The most convincing call to action? The most accurate? The highest grossing? Driving the most engagement? What about the topic (any topic) that you could tell the /most interesting surprise/ about?
If Paul Graham didn’t run this company he certainly would not make it to the front page for his lazy philosophy.
Hemingway once said just write the truest sentence you can think of and I think he was right. Good writing and good essays are truthful in a way that wouldn't be expected from commercial and marketing copy. But to write truthfully one must know what is true and this is surprisingly hard.
On the most important topic you could tell people something surprising about. And all those things you said. And … and (yes, that “and”) … so much more!
We are talking about the join of all essay joins. The essay supremum. By definition
I think we can agree there is a limit to the length of this essay. Proof by absurdum: if the essay is too long to read, that would imply unread word choices make a difference. So there is finite length N.
Now we just search for it. Unleash the monkeys! Or today, unleash the competitive adversarial AI cohort!
We can find it, just not copyright it. Which I think, is the best outcome for humanity. Assuming this essay is aligned with our interests, but we have set that unboxing in motion now so it’s not worth worrying about
I think it’s best to maintain some humor when talking about mythical bests, one way or another
Anyone can nitpick anyone by listing whatabouts they didn't intend. Whatabout this OTHER sense of the word "best". It's in the dictionary. You didn't address it, therfore you're a lazy man of straw. The only defense to that type of attack is to write everything in a way that never chooses any one path, spends all it's time mounting a defense to every whatabout, vaguely floating over eggshells, immune to attack. Who wants to read something like that? Or, you can trust the reader to try to understand the context. The context is a man who calls himself an essayist, has about a hundred essays spanning a decade, all in a very distinct style, where most folks reading them are fans of the prior ones. The context is the Paul Graham Essay sense of the word essay. It's not discussing emotional, spoken, money grossing essays. And to help the reader not get hung up on those whatabouts, he even explicitly spelled what sense of best he is talking about.
I’m still surprised that this essay didn’t explore the nature of the audience. I’m not disagreeing with your take about the dangers of straw men, but PG does seem very much in the vein of essays are for communicating interesting stuff, or fun stuff, or provocative stuff. To someone! And it seems like too long of an essay to discover by the end this serious omission. A timeless essay is one that retains meaning to a person, or maybe many people, over the course of time. PG spent a while trying to explore the message in this essay and no time on trying to understand the audience.
What a weird comment that could extend to literally any post here.
Maybe we should just delete HN and replace it with a link to a climate change non profit, since apparently we're better off platforming that than discussing anything else.
Most people in society throughout the ages have not done the majority of their thinking. It has been handed to them from a pulpit or something similar. Even without an explicit religion, people still want someone to follow, so now successful people are followed. Successful people don't have to be intelligent or even moral.
As a commoner, you can accept that pollution is terrible, but then immediately think that it can't be a big deal because the people on high are flying around in private jets and living in mansions. Do you think we can convince people of the importance of having a sustainable environment, while the people on high pay lip service to the cause and then blatantly contradict themselves by showing us how they live? How do you get common people to care about their environmental footprint when they're constantly told not to be content with what they've got?
How does humanity rein in its covetousness? Do you think humans can live sustainably without solving that problem?
And the real shame is that he gets so close: he talks about discovery, about the intersection of science and technology and the broader world, he identifies the importance of doing things to learn enough to write about them, and most importantly: having an outrageous question with a real and alarming insight lurking around the corner as an answer and thereby avoids vaporous rhapsodizing.
So I’ll ask an outrageous question about which pg has both deep insight and over a decade of lived experience to ground an answer on: is YC still a good thing? I’ll ask a few corollary questions to illustrate.
He talks about the kinds of tests you hack to get ahead in some vague elsewhere: is getting ahead in YC, or the Valley, or the technology business still about merit and capability and being relentlessly resourceful rather than optics, connections, and flexibility? Is it about garages with Ethernet cables snaking everywhere more or less than knowing one’s way around the Rosewood Sand Hill?
His first citation as a reviewer is Sam Altman: is @sama still his pick for most capable founder and best person to guide the sprawling empire that YC sits at the heart of?
I don’t find any of those things obvious, and I think a candid essay about a set of very timely questions would be the most important essay he’d ever written.