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

Mistral releases Devstral2 and Mistral Vibe CLI

mistral.ai

Post reply on HN
Print view View original

201–210 of 363 posts

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#201

Post by Etheryte »

th0ma5 wrote: post #141
Jimmc414 wrote: post #109

Earlier quoted context omitted.

We are getting to the point that its not unreasonable to think that "Generate an SVG of a pelican riding a bicycle" could be included in some training data. It would be a great way to ensure an initial thumbs up from a prominent reviewer. It's a good benchmark but it seems like it would be a good idea to include an additional random or unannounced similar test to catch any benchmaxxing.

If this had any substance then it could be criticized, which is what they're trying to avoid.

How? There's no way for you to verify if they put synthetic data for that into the dataset or not.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#202

Post by zmmmmm »

troyvit wrote: post #191
zmmmmm wrote: post #181

Earlier quoted context omitted.

I think Aider is closest to what you want. The chat interface is optimal to me because you often are asking questions and seeking guidance or proposals as you are making actual code changes. On reason I do like it is that its default mode of operation is to make a commit for each change it makes. So it is extremely clear what the AI did vs what you did vs what is a hodge podge of both. As others have mentioned, you c…

Aider can be a chat interface and it's great for that but you can also use it from your editor by telling it to watch your files.[1] So you'd write a function name and then tell it to flesh it out. function factorial(n) // Implement this. AI! Becomes: function factorial(n) { if (n === 0 || n === 1) { return 1; } else { return n \* factorial(n - 1); } } Last I looked Aider's maintainer has had to focus on other things…

> I don't want to be tied to just one model.

Very much this for me - I really don't get why, given a new models are popping out every month from different providers, people are so happy to sink themselves into provider ecosystems when there are open source alternatives that work with any model.

The main problem with Aider is it isn't agentic enough for a lot of people but to me that's a benefit.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#203

Post by kristianp »

embedding-shape wrote: post #126
chrsw wrote: post #76

Earlier quoted context omitted.

> run locally for agentic coding. Nowadays I mostly use GPT-OSS-120b for this What kind of hardware do you have to be able to run a performant GPT-OSS-120b locally?

RTX Pro 6000, ends up taking ~66GB when running the MXFP4 native quant with llama-server/llama.cpp and max context, as an example. Guess you could do it with two 5090s with slightly less context, or different software aimed at memory usage efficiency.

That has 96GB GDDR7 ECC, to save people looking it up.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#204

Post by kristianp »

eavan0 wrote: post #165

I'm glad it's not another LLM CLI that uses React. Vibe-cli seems to be built with https://github.com/textualize/textual/

I'm not excited that it's done in python. I've had experience with Aider struggling to display text as fast as the llm is spitting it out, though that was probably 6 months ago now.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#205

Post by willm »

kristianp wrote: post #204
eavan0 wrote: post #165

I'm glad it's not another LLM CLI that uses React. Vibe-cli seems to be built with https://github.com/textualize/textual/

I'm not excited that it's done in python. I've had experience with Aider struggling to display text as fast as the llm is spitting it out, though that was probably 6 months ago now.

Python is more than capable of doing that. It’s not an issue of raw execution speed.

https://willmcgugan.github.io/streaming-markdown/

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#206

Post by kristianp »

syntaxing wrote: post #163

Extremely happy with this release, the previous Devstral was great but training it for open hands crippled the usefulness. Having their own CLI dev tool will hopefully be better

Can you explain "training it for open hands"? I can't parse the meaning.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#207

Post by tgtweak »

princehonest wrote: post #79

Let's say you had a hardware budget of $5,000. What machine would you buy or build to run Devstral Small 2? The HuggingFace page claims it can run on a Mac with 32 GB of memory or an RTX 4090. What kind of tokens per second would you get on each? What about DGX Spark? What about RTX 5090 or Pro series? What about external GPUs on Oculink with a mini PC?

dual 3090's (24GB each) on 8x+8x pcie has been a really reliable setup for me (with nvlink bridge... even though it's relatively low bandwidth compared to tesla nvlink, it's better than going over pcie!)

48GB of vram and lots of cuda cores, hard to beat this value atm.

If you want to go even further, you can get an 8x V100 32GB server complete with 512GB ram and nvlink switching for $7000 USD from unixsurplus (ebay.com/itm/146589457908) which can run even bigger models and with healthy throughput. You would need 240V power to run that in a home lab environment though.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#208

Post by simonw »

giancarlostoro wrote: post #192
simonw wrote: post #167

The system prompt and tool prompts for their open source (Apache 2 licensed) Python+Textual+Pydantic CLI tool are fun to read: core/prompts/cli.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c... core/prompts/compact.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c... .../prompts/bash.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c... .../prompts/grep.md https://github.co…

Based on your experience with Claude Code, how does Mistral Vibe compare?

I've not spent enough time with Mistral Vibe yet for a credible comparison, but given what I know about the underlying models (likely-1T-plus Opus 4.5 compared to the 123B Devstral 2) I'd be shocked if Vibe could out-perform Claude Code for the kinds of things I'm using it for.

Here's n example of the kinds of things I do with Claude Code now: https://gistpreview.github.io/?b64d5ee40439877eee7c224539452... - that one involved several from-scratch rewrites of the history of an entire Git repo just because I felt like it.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#209

Post by simonw »

bravetraveler wrote: post #178
dugidugout wrote: post #144

Earlier quoted context omitted.

Condescending and disrespectful to whom? Everybody wholsale? This doesnt seem reasonable? Please elaborate.

Not sure if I'd use the same descriptions so pointedly , but I can see what they mean. It's perfectly fine to link for convenience, but it does feel a little disrespectful/SEO-y to not 'continue the conversation' . A summary in the very least, how exactly it pertains. Sell us. In a sense, link-dropping [alone] is saying: "go read this and establish my rhetorical/social position, I'm done here" Imagine meeting an auth…

I've genuinely been answering the question "what if the labs are training on your pelican benchmark" 3-4 times a week for several months at this point. I wrote that piece precisely so I didn't have to copy and paste the same arguments into dozens of different conversations.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#210

Post by stusmall »

clusterhacks wrote: post #162
monster_truck wrote: post #136

Earlier quoted context omitted.

I'd throw a 7900xtx in an AM4 rig with 128gb of ddr4 (which is what I've been using for the past two years) Fuck nvidia

You know, I haven't even been thinking about those AMD gpus for local llms and it is clearly a blind spot for me. How is it? I'd guess a bunch of the MoE models actually run well?

I've been running local models on an AMD 7800 XT with ollama-rocm. I've had zero technical issues. It's really just the usefulness of a model with only 16GB vram + 64GB of main RAM is questionable, but that isn't an AMD specific issue. It was a similar experience running locally with an nvidia card.
Post reply on HN