Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Codestral: Mistral's Code Model

mistral.ai

Post reply on HN
Print view View original

51–60 of 225 posts

Re: Codestral: Mistral's Code Model

#51

Post by skydhash »

colesantiago wrote: post #17

I'm so happy now LLMs are democratising access to programming, especially open models like what Meta with Llama and Mistral is doing with Codestral are doing. The abundance of programming is going to allow almost everyone to become a great programmer. This is so exciting to see and each day programming is becoming a solved problem so we can focus on other things.

Shadow libraries did more to democratize anything than LLMs. And following a book like Elixir in Action (Manning) will get you there faster than chatting with LLMs or copilot generating code for you.

Re: Codestral: Mistral's Code Model

#52

Post by bottom999mottob »

bongodongobob wrote: post #45
TechDebtDevin wrote: post #34

Earlier quoted context omitted.

Damn, show us your brilliant prompt then. LLMs cannot do this, not even in python, of which there are libraries like Blacksheep that honestly make it a trivial task.

My point is that you shouldn't expect to one shot everything. Have it start by writing a spec, then outline classes and methods, then write the code, and feed it debug stuff.

Exactly, expecting one shot 100% working code with one prompt is ridiculous at this point. It's why libraries like Aider are so useful, because you can iteratively diff generated code until it's useable.

Re: Codestral: Mistral's Code Model

#53

Post by wing-_-nuts »

andruby wrote: post #10

This is an open weights 22B model. The download on Huggingface is 44GB. Is there a rule-of-thumb estimate for how much RAM this would need to be used locally? Is the RAM requirement the same for a GPU and "unified" RAM like Apple silicon?

Wait for a gguf release of this and it will fit neatly into a 3090 with a decent quant. I'm excited for this model and I'll be adding it to my collection.

Re: Codestral: Mistral's Code Model

#54

Post by TechDebtDevin »

bongodongobob wrote: post #45
TechDebtDevin wrote: post #34

Earlier quoted context omitted.

Damn, show us your brilliant prompt then. LLMs cannot do this, not even in python, of which there are libraries like Blacksheep that honestly make it a trivial task.

My point is that you shouldn't expect to one shot everything. Have it start by writing a spec, then outline classes and methods, then write the code, and feed it debug stuff.

I see your point but hand holding isn't really a good way to benchmark a models coding capabilities.

Re: Codestral: Mistral's Code Model

#55

Post by ben_w »

TechDebtDevin wrote: post #34
bongodongobob wrote: post #30

Earlier quoted context omitted.

Cool, you've identified that your prompt is inadequate for the task. 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?'

Damn, show us your brilliant prompt then. LLMs cannot do this, not even in python, of which there are libraries like Blacksheep that honestly make it a trivial task.

Prompts like yours (I ask them for a fluid dynamics simulator which also doesn't succeed) inform us of the level they have reached. A useful benchmark, given how many of the formal ones they breeze through.

I'm glad they can't quite manage this yet. Means I still have a job.

Re: Codestral: Mistral's Code Model

#56

Post by smokel »

colesantiago wrote: post #17

I'm so happy now LLMs are democratising access to programming, especially open models like what Meta with Llama and Mistral is doing with Codestral are doing. The abundance of programming is going to allow almost everyone to become a great programmer. This is so exciting to see and each day programming is becoming a solved problem so we can focus on other things.

In my experience these tools amplify the quality of a programmer.

I have seen good programmers dramatically increase their productivity, but I've also seen others copy-pasting for loops inside other for loops where one loop would definitely suffice. We're not quite there yet.

Re: Codestral: Mistral's Code Model

#57

Post by croes »

>Usage Limitation

- You shall only use the Mistral Models and Derivatives (whether or not created by Mistral AI) for testing, research, Personal, or evaluation purposes in Non-Production Environments;

- Subject to the foregoing, You shall not supply the Mistral Models, Derivatives, or Outputs in the course of a commercial activity, whether in return for payment or free of charge, in any medium or form, including but not limited to through a hosted or managed service (e.g. SaaS, cloud instances, etc.), or behind a software layer

Re: Codestral: Mistral's Code Model

#58

Post by Rastonbury »

jasonjmcghee wrote: post #44
rohansood15 wrote: post #16

Earlier quoted context omitted.

Copilot primarily uses GPT-3.5, which is outclassed by Llama3-70B. And this model claims to be slightly better than Llama3-70B. Edit: For those who don't believe me, https://github.com/microsoft/vscode-copilot-release/issues/6... . Gpt-4 for chat, 3.5 for code.

GitHub Copilot uses GPT-3.5? I was under the impression it was a custom codex model with a surrogate local model as per https://github.blog/2023-02-14-github-copilot-now-has-a-bett... When did this change?

When it first launched it, I too didn't know they had changed the model from the original codex which came similar time as gpt-3.5

Re: Codestral: Mistral's Code Model

#60

Post by Closi »

TechDebtDevin wrote: post #34
bongodongobob wrote: post #30

Earlier quoted context omitted.

Cool, you've identified that your prompt is inadequate for the task. 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?'

Damn, show us your brilliant prompt then. LLMs cannot do this, not even in python, of which there are libraries like Blacksheep that honestly make it a trivial task.

Break your prompt up into smaller pieces and it can.
Post reply on HN