Did you try to use GPT 3.5? Our testing is it isn't great, using GPT 4 or some of the specialized trained versions of GPT 4 (there's one with good reviews called Lisp Engineer) our experience has been different.
It is not replacing engineers, it isn't one where you give it a broad set of requirements and it just goes and builds, it is helping increase productivity, to get folks through areas where they need to bounce ideas off of someone.
We're coding mostly in Python, C++, and .NET Core where I do expect it'll have a much deeper set of training data than it will for Lisp (and even for those languages we're getting marginally better performance from specialized engines than we are general GPT 4).
The non-OpenAI other coding AIs so far are all performing worse for us than GPT4. We've done testing against LeetCode challenges and a bunch of other things.
If only these LLMs were decent at C#. Unfortunately, they heavily lean towards very old data, would call obsolete APIs and in a style that is generally against what is considered to be idiomatic and terse.
Functionally identical but such cruft accumulates per each single piece of functionality you ask it to implement. And this example is one where the output was at least coherent and doing its job, many more are worse.
> We're coding mostly in Python, C++, and .NET Core where I do expect it'll have a much deeper set of training data than it will for Lisp
I can't imagine how malformed bracketing is due to insufficient training set.
And nor it seems can ChatGPT: "I've encountered numerous examples of Lisp code during my training, covering different applications and techniques within the language. Whether it's simple examples or more complex implementations, I've seen quite a bit of Lisp code."
You tried the very first iteration of an LLM-based chat assistant, were unsatisfied with it because it couldn't match Lisp parentheses, and went on to form an opinion about the value of these tools and implicitly the intelligence of the people who use them. That speaks more to your preconceptions than it does to the state of better tools like Copilot or GPT-4.
You didn't label it (which, btw, is a faux pas), but it's obvious from your replies that this wasn't an Ask HN, it was a Tell HN. You have absolutely no interest in what the rest of us have to say.
Nevertheless, I'll try once more for luck: Basing your opinions about LLMs on your experience with GPT-3.5 is a mistake. If you don't want to use LLMs at all because you have preconceptions, that's fine, but don't pretend that you've sampled LLMs and found them lacking for professional coding when you haven't tried the professional tools.
Yes. ChatGPT-3.5 was the very first LLM-based chat assistant that was announced on Nov 30, 2022 [0]. It hasn't gotten better since then, just more censored and faster.
It followed GPT-1 (which was only interesting to people who were already in the know), GPT-2 (which was neat but widely recognized as pretty useless and again, not something normal people noticed) and GPT-3 (which was cool, but didn't provide a chat interface, it could only complete texts, so it made a decent base for the early versions of Copilot).
[0] "ChatGPT is fine-tuned from a model in the GPT-3.5 series, which finished training in early 2022." https://openai.com/index/chatgpt/
At 260 million passengers per year, that's $6 per ticket on a 20 year payback. By my understanding this is affordable as JFK is around $15 per passenger in fees.
That also assumes that people will want to travel the same amounts in the future or that other hubs won’t also be expanding and competing. In my opinion the main problem with Dubai is there isn’t a reason to actually visit it or spend time there for most people. It’s hot, in a dusty desert, and the main attractions are luxuries like shopping. But maybe that’s why this proposal seems more based on business (shopping and logistics).
Yes Dubai is a satire, not a city. Most passengers don't stop but transit there. The reason they choose such route - Dubai is a hub that offers 1000s of routes.
My alternative is 1 extra leg to avoid Dubai or Qatar. Occasionally that works for me - I do have extra days and funds to checkout cities. Most people don't.
Rough math, $1,000 for the raw stone, $5,000 of travel and time to source... $80k sale price with 250 hours of cutting work, $300/hour for master gemcutter, seems very fair.
Here's human drivers navigating in a similar way in a large intersection in Addis Abada (Ethiopia), I envision white light basically enabling this: https://youtu.be/VPbUpdmAfck
What is actually being enabled, and is it more efficient than a regular green-yellow-red intersection? If you watch on 1x, this seems like a horribly slow/inefficient intersection.
TLDR: This is a real thing, turbines have built in protection, and there innovating on the whole system to really do this. It's a potential game changer vs. trying to build seawalls or levees.
Disabling cookies will cause _more_ of the "cookie prompts" to appear, not less. Some pages these days even will prevent visiting them unless they can set a cookie...
Also, cookies are not the only method of tracking which is supposed to be disabled when you hit Deny.
Doing a side by side. MM doesn't have visible front teeth, his ears are smaller and fully black, the silhouette is different. But the shape of the face and features, including where the shape of the black fur decends (at the widows peak?), the eyebrows, the eyes with white, all look quite similar. To me it's much closer to a modern Mickey than the original flat black and white.
Perspective as CEO of a backup and disaster recovery company...
A lot of folks now have ransomware protected backups for critical data so they aren't paying for decryption keys.
This has escalated to hack and release, the attackers are now exfiltrating data and threatening to make it public in addition to encrypting it on the host system.
