Live data from Hacker News

Code Llama, a state-of-the-art large language model for coding

ai.meta.com

391–400 of 525 posts

Re: Code Llama, a state-of-the-art large language model for coding

#391
post #122

Never before in the history of mankind was a group so absolutely besotted with the idea of putting themselves out of a job.

If we get to the point where these large language models can create complete applications and software solutions from design specs alone, then there's no reason to believe that this would be limited to merely replacing software devs.

It would likely impact a far larger swath of the engineering / design industry.

Re: Code Llama, a state-of-the-art large language model for coding

#392

Business opportunity: I'd pay money for NICE desktop software that can run all these different models (non-subscription, "2-year updates included, then discount pricing" modal perhaps). My wishlist: - Easy plug & play model installation, and trivial to change which model once installed. - Runs a local web server, so I can interact with it via any browser - Ability to feed a model a document or multiple documents and…

You want a polished product and something that can run all sorts of different models. I don't know that both are possible at the same time.

Re: Code Llama, a state-of-the-art large language model for coding

#393

Earlier quoted context omitted.

it's not that though, there's several other typical optimisations in there just not the super obvious one that demonstrates extremely basic understanding of what a prime number is

Having "extremely basic understanding" of prime numbers immediately at one's command is important for approximately 0% of software engineering jobs. If you instant-fail a candidate for this, it says a lot more about you and your organization than the candidate.

Approx 0% of devs need to know what the earth is, but from lots of interviews I've given I've found consistent correlation between lack of basic knowledge and lack of ability to solve many things. It was so strong we found it much more cost effective to cut people early that didn't know at least a few of some standard knowledge items.

Re: Code Llama, a state-of-the-art large language model for coding

#395

Earlier quoted context omitted.

it's not that though, there's several other typical optimisations in there just not the super obvious one that demonstrates extremely basic understanding of what a prime number is

I'm mad at myself now that it has eaten 15 minutes of my time trying to come up with the right optimization. What's the trick? 2, +1, and then +2 from there on seems obvious but once you get to 9 is it worth building a list of nonprimes to skip?

There's lots of more advanced optimizations, which would be an interesting avenue for discussion in an interview, but the drain dead algorithm would just use +2 instead of +1

Re: Code Llama, a state-of-the-art large language model for coding

#396
post #384

Earlier quoted context omitted.

I work for a Fortune 100 company with 80,000+ employees. All of us are explicitly forbidden from using any sort of AI/LLM tool without written permission from the head of legal AND the CEO. In other words, nobody is going to get permission. The concerns are 2 fold - 1. We might inadvertently use someone else’s intellectual property. 2. Someone else might gain access to our intellectual property. What you are describi…

It's basically the same thing in our company, too. They basically put a similar rule in place that prevents anyone from using e.g. Chat GPT. Little do they know that all software devs within the company are using co-pilot and the company is even paying for it. It's quite a funny situation tbh..

Except, at my company they block software like that. Not only do they block it, but if you try to go to it a security person will immediately call your manager and ask what you are doing.

Re: Code Llama, a state-of-the-art large language model for coding

#397

Business opportunity: I'd pay money for NICE desktop software that can run all these different models (non-subscription, "2-year updates included, then discount pricing" modal perhaps). My wishlist: - Easy plug & play model installation, and trivial to change which model once installed. - Runs a local web server, so I can interact with it via any browser - Ability to feed a model a document or multiple documents and…

I work for a Fortune 100 company with 80,000+ employees. All of us are explicitly forbidden from using any sort of AI/LLM tool without written permission from the head of legal AND the CEO. In other words, nobody is going to get permission. The concerns are 2 fold - 1. We might inadvertently use someone else’s intellectual property. 2. Someone else might gain access to our intellectual property. What you are describi…

There may also be a third more important concern: AI/LLM generated works are not generally copyrightable.[1]

The Copilot lawsuit should answer concern #1 more definitively.

#2 is already solved by running your own model or using Azure OpenAI.

[1]https://www.copyright.gov/ai/ai_policy_guidance.pdf

Re: Code Llama, a state-of-the-art large language model for coding

#398

How much am I’m missing out on with tools like this or code pilot, compared to using GPT-4? I guess since Xcode doesn’t have a good plug-in architecture for this I began experimenting more with a chat interface. So far gpt-4 has seemed quite useful for generating code, reviewing code for certain problems, etc.

Editor plugins are fantastic about completing based on a pattern. That's the main thing you're missing out on imo - it's worth it to hit tab, but not to copy/paste and say "finish this line for me, it looks almost like the one above."

There's also the real-time aspect where you can see that it's wrong via the virtual text, type a few characters, then it gets what you're doing and you can tab complete the rest of the line.

It's faster to converse with when you don't have to actually have a conversation, if that makes sense? The feedback loop is much shorter and doesn't require natural language, or nearly as much context switching.

Re: Code Llama, a state-of-the-art large language model for coding

#399
post #357

Earlier quoted context omitted.

Change company. Honestly. If you go as far as to forbid your partners in crime (workers sigh..) to explore new uncharted territory at all - well ya know someone will/might just win by not doing that.

This is particular, specifically problematic territory. I cannot imagine handing over proprietary data to a third party without a contract in place for how that data is stored and used. It’s not about innovation, it’s about using someone else’s tools without ownership. For the other case, it’s both about integrity in owning your own work, and a shield from legal consequences. These things should be very relevant to a…

> I also don’t know any professional devs who have used tools like copilot and said they were anything but a toy.

Really? I'm academic now but I find Copilot at least moderately helpful when I'm writing a library. It's pretty good a lot of boilerplate functions, docstrings, regex, etc. I certainly don't want to go back to not using it, my code is a lot closer to production quality now and looks nicer.

Thinking back to my days in back-end it seems like it would have been very helpful/sped things up so I'm surprised to hear it's just a toy but I've been out of the professional game for a while now. What's the main criticism?

Re: Code Llama, a state-of-the-art large language model for coding

#400

Business opportunity: I'd pay money for NICE desktop software that can run all these different models (non-subscription, "2-year updates included, then discount pricing" modal perhaps). My wishlist: - Easy plug & play model installation, and trivial to change which model once installed. - Runs a local web server, so I can interact with it via any browser - Ability to feed a model a document or multiple documents and…

We are doing this with https://Faraday.dev - would love to chat more - my email is on my profile!
Post reply on HN