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

141–150 of 363 posts

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#141

Post by th0ma5 »

Jimmc414 wrote: post #109
simonw wrote: post #33

llm install llm-mistral llm mistral refresh llm -m mistral/devstral-2512 "Generate an SVG of a pelican riding a bicycle" https://tools.simonwillison.net/svg-render#%3Csvg%20xmlns%3D... Pretty good for a 123B model! (That said I'm not 100% certain I guessed the correct model ID, I asked Mistral here: https://x.com/simonw/status/1998435424847675429 )

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.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#142

Post by iberator »

simonw wrote: post #33

llm install llm-mistral llm mistral refresh llm -m mistral/devstral-2512 "Generate an SVG of a pelican riding a bicycle" https://tools.simonwillison.net/svg-render#%3Csvg%20xmlns%3D... Pretty good for a 123B model! (That said I'm not 100% certain I guessed the correct model ID, I asked Mistral here: https://x.com/simonw/status/1998435424847675429 )

Where did you get llm tool from?!

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#143

Post by InsideOutSanta »

I gave Devstral 2 in their CLI a shot and let it run over one of my smaller private projects, about 500 KB of code. I asked it to review the codebase, understand the application's functionality, identify issues, and fix them.

It spent about half an hour, correctly identified what the program did, found two small bugs, fixed them, made some minor improvements, and added two new, small but nice features.

It introduced one new bug, but then fixed it on the first try when I pointed it out.

The changes it made to the code were minimal and localized; unlike some more "creative" models, it didn't randomly rewrite stuff it didn't have to.

It's too early to form a conclusion, but so far, it's looking quite competent.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#144

Post by dugidugout »

th0ma5 wrote: post #138
simonw wrote: post #134

Earlier quoted context omitted.

I wrote about that possibility here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

[flagged]

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

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#145

Post by whimblepop »

whimsicalism wrote: post #54
jrm4 wrote: post #48

Earlier quoted context omitted.

You're presently illustrating exactly why Stallman et al were such sticklers about "Free Software." "Open Source" is nebulous. It reasonably works here, for better or worse.

Free software to me means GPL and associates, so if that is what Stallman was trying to be a stickler for - it worked. Open source has a well understood meaning, including licenses like MIT and Apache - but not including MIT but only if you make less than $500million dollars, MIT unless you were born on a wednesday, etc.

MIT and Apache are free software licenses in Stallman's sense, and the FSF has always been clear about it.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#146

Post by tarsinge »

lagniappe wrote: post #122
tarsinge wrote: post #114

Earlier quoted context omitted.

In what year was it meaningful to have pelicans riding bicycles?

SVG is a current standard. Do not be coy just to satisfy your urge to disagree.

The website is live and renders correctly on my Safari mobile: https://www.spacejam.com/1996/

I may have missed something but where are we saying the website should be recreated with 1996 tech or specs? The model is free to use any modern CSS, there is no technical limitations. So yes I genuinely think it is a good generalization test, because it is indeed not in the training set, and yet it is easy an easy task for a human developer.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#148

Post by MLgulabio »

InsideOutSanta wrote: post #143

I gave Devstral 2 in their CLI a shot and let it run over one of my smaller private projects, about 500 KB of code. I asked it to review the codebase, understand the application's functionality, identify issues, and fix them. It spent about half an hour, correctly identified what the program did, found two small bugs, fixed them, made some minor improvements, and added two new, small but nice features. It introduced…

On what hardware did you run it?

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#150

Post by hadlock »

embedding-shape wrote: post #4

Look interesting, eager to play around with it! Devstral was a neat model when it released and one of the better ones to run locally for agentic coding. Nowadays I mostly use GPT-OSS-120b for this, so gonna be interesting to see if Devstral 2 can replace it. I'm a bit saddened by the name of the CLI tool, which to me implies the intended usage. "Vibe-coding" is a fun exercise to realize where models go wrong, but for…

>vibe-coding

A surprising amount of programming is building cardboard services or apps that only need to last six months to a year and then thrown away when temporary business needs change. Execs are constantly clamoring for semi-persistent dashboards and ETL visualized data that lasts just long enough to rein in the problem and move on to the next fire. Agentic coding is good enough for cardboard services that collapse when they get wet. I wouldn't build an industrial data lake service with it, but you can certainly build cardboard consumers of the data lake.

Post reply on HN