Meta Llama 3 - Hackdot

Re:Meta Llama 3 by fnordlord on Thursday April 18, 2024 @12:47PM (#40078168)

Do you mind my asking, if you're working on private codebases, how you go about using GPT/Claude as a code assistant? I'm just removing IP and pasting into their website's chat interface. I feel like there's got to be something better out there but I don't really know anyone else that's using AI code assistance at all.

[ Parent | on HN ]

Re:Meta Llama 3 by Zambyte on Thursday April 18, 2024 @12:54PM (#40078250)

Personally I don't paste anything. I ask for code examples that demonstrate what I want, and then I adapt it to my needs. It's definitely less powerful than directly sharing code, but it is what it is.

I also run a personal language model server, but that is far less capable than the models available as services. It can still be better than nothing for code O can't share with APIs.

I also use gpt.el a but for editor integration, but I honestly haven't workeded that into my workflow very much yet.

[ Parent | on HN ]

Re:Meta Llama 3 by paradite on Thursday April 18, 2024 @01:45PM (#40078767)

I built a desktop tool to help reduce the amount of copy-pasting and improve the output quality for coding using ChatGPT or Claude: https://prompt.16x.engineer/

[ Parent | on HN ]

Re:Meta Llama 3 by bpiche on Thursday April 18, 2024 @12:56PM (#40078286)

Vscode with GitHub copilot is great, been using it for about a year and a half, no complaints. The business tier allegedly doesn’t save/train on your data

[ Parent | on HN ]

Re:Meta Llama 3 by danenania on Thursday April 18, 2024 @01:09PM (#40078423)

I'm building Plandex (https://github.com/plandex-ai/plandex), a terminal-based AI coding tool which currently uses the OpenAI api--I'm working on support for Anthropic and OSS models right now and hoping I can ship it later today.

You can self-host it so that data is only going to the model provider (i.e. OpenAI) and nowhere else, and it gives you fine-grained control of context, so you can pick and choose exactly which files you want to load in. It's not going to pull in anything in the background that you don't want uploaded.

There's a contributor working on integration with local models and making some progress, so that will likely be an option in the future as well, but for now it should at least be a pretty big improvement for you compared to the copy-paste heavy ChatGPT workflow.

[ Parent | on HN ]

Re:Meta Llama 3 by fnordlord on Thursday April 18, 2024 @01:13PM (#40078466)

Very cool! I'll take a look.

[ Parent | on HN ]

Re:Meta Llama 3 by wincy on Thursday April 18, 2024 @12:51PM (#40078212)

I haven’t used it but I’ve heard https://cursor.sh/ might work?

[ Parent | on HN ]

Re:Meta Llama 3 by BoorishBears on Thursday April 18, 2024 @12:50PM (#40078201)

Use the API (or a product that uses the API)

If you can trust Azure or AWS or GCP with your IP, you can get Claude 3 and GPT-4 Turbo through at least one of them

If your IP is so secret you can't do that, then I wouldn't imagine you'd be using the chat interface

[ Parent | on HN ]

Re:Meta Llama 3 by free_bip on Thursday April 18, 2024 @12:55PM (#40078271)

Unless you have the privilege of being an enterprise customer with an SLA guaranteeing privacy, there's not much you can do other than using local models. I believe OpenAI says they don't train based on API requests but that's more of a "trust me bro" than any kind of guarantee.

[ Parent | on HN ]

Re:Meta Llama 3 by zamadatix on Thursday April 18, 2024 @03:19PM (#40079786)

Team and Enterprise come with the non-training guarantee, free and premium do not. Pretty much anyone can sign up for Team (I have, and I'm not a company) but you need to buy at least 2 seats for a total of $50/m. The rate limits are much better with that as well though.

[ Parent | on HN ]