[dead]
Mistral releases Devstral2 and Mistral Vibe CLI
311–320 of 363 posts
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#312Earlier quoted context omitted.
I wrote about that possibility here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...
Hi Simon! Love your work! Our of curiosity - how many pelican-cycling samples do you produce. Curious about the variance here. Thanks!
I've lost count, but there are 85 posts with that tag here: https://simonwillison.net/tags/pelican-riding-a-bicycle/
I need to extract them all into a formal collection.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#313Earlier 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.
I wrote about that possibility here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...
Aiden is perhaps misinformed. From a Bing search performed just now.
> Yes, I am familiar with the "pelican riding a bicycle" SVG generation test. It is a benchmark for evaluating the ability of AI models, particularly large language models (LLMs) and multi-modal systems, to generate original, high-quality SVG vector graphics based on a deliberately unusual and complex prompt. The benchmark was popularized by Simon Willison, who selected the prompt because:
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#314Earlier quoted context omitted.
> I couldn't care less that the term is "diluted" and that makes it harder It also makes life harder for individuals and small companies, because this is not Open Source . It's incompatible with Open Source, it can't be reused in other Open Source projects. Terms have meanings. This is not Open Source, and it will never be Open Source.
> It also makes life harder for individuals and small companies, because this is not Open Source. It's incompatible with Open Source, it can't be reused in other Open Source projects. I'm amazed at the social engineering that the megacorps have done with the whole Open Source (TM) thing. They engineered a whole generation of engineers to advocate not in their own self-interest, nor for the interest of the little peop…
Nobody cares if they use a license that inconveniences megacorporations. The issue is how they try to present the license.
> start bullying everyone else to change their language
Either words matter or they do not. If words matter, then trying to dilute the term is a bad thing because it tries to weaken something that matters. If words do not matter, then the people who "bully everyone" can be easily ignored. You cannot have these two things at the same time.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#315Earlier quoted context omitted.
Maybe they are just trying to be funny.
Their chat was called "Le Chat" - it's just their style. And while it may miss the HN crowd, one of the main selling-points of AI coding is the ease and playfulness.
It's still called "Le Chat" (which means The Cat in French), hence the occasional pun with a cat icon in various places on their website.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#316Earlier quoted context omitted.
Hi Simon! Love your work! Our of curiosity - how many pelican-cycling samples do you produce. Curious about the variance here. Thanks!
I've lost count, but there are 85 posts with that tag here: https://simonwillison.net/tags/pelican-riding-a-bicycle/ I need to extract them all into a formal collection.
I think the parent poster might be asking about generations per model-test. Atleast that's what I understood.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#317Let'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?
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
Or a Strix Halo Ryzen AI Max. Lots of "unified" memory that can be dedicated to the GPU portion, for not that expensive. Read through benchmarks to know if the performance will be enough for your needs though.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#318Earlier 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
Or a Strix Halo Ryzen AI Max. Lots of "unified" memory that can be dedicated to the GPU portion, for not that expensive. Read through benchmarks to know if the performance will be enough for your needs though.
Do you think the larger Mistral model would fit on a AI Max 395? I've been thinking about buying one of those machines, but haven't convinced myself yet.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#319Yet another CLI. Why does every AI provider need to have its own tool, instead of contributing to existing tools like Roo Code or Opencode?
I just end up using most of these models with Claude Code as the tooling because it just seems to work better than anything else. Crush also works well.
Re: Mistral releases Devstral2 and Mistral Vibe CLI
#320Earlier quoted context omitted.
Are any of them integrated with git? AFAIK, you'd have to instruct them to use git for you if you don't want to do it manually. Imagine a GUI built around git branches + agents working in those branches + tooling to manage the orchestration and small review points, rather than "here's a chat and tool calling, glhf".
> Are any of them integrated with git? All of the models that can do tool calls are typically good enough to use Git. Just this week I used both Claude Code and Codex to look at unstaged/staged changes and to review them multiple times, even do comparison between a feature branch and the main branch to identify why a particular feature might have broken in the feature branch.
> All of the models that can do tool calls are typically good enough to use Git.
But again, it's the "user message > llm reason > llm tool call > tool response > llm reason > llm response" flow I think is inefficient and not good enough. It's a lazy solution built on top of the chat flow.
What I imagined would exist by now would be something smarter, where you don't say "Ok, now please commit this" or whatever.
I already have a tool for myself that launch Codex, Claude Code, Qwen Code(r?) and Gemini for each change I do, and automatically manage them into git branches, and lets me diff between what they do and so on.
Yet I still think we haven't really figured out a good UX for this.