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

351–360 of 363 posts

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#351

Post by rootnod3 »

embedding-shape wrote: post #62
pdntspa wrote: post #19

Earlier quoted context omitted.

> But where are the professional tools, meant to be used for people who don't want to do vibe-coding, but be heavily assisted by LLMs? Something that is meant to augment the human intellect, not replace it? Claude Code not good enough for ya?

Claude Code has absolutely zero features that help me review code or do anything else than vibe-coding and accept changes as they come in. We need diff-comparisons between different executions, tailored TUI for that kind of work and more. Claude Code is basically a MVP of that. Still, I do use Claude Code and Codex daily as there is nothing better out there currently. But they still feel tailored towards vibe-coding…

Might be a weird suggestion but here we go: - use whatever diff tool you used before LLMs came around and actually review the code? Just a suggestion. If people claim they always examine the full output at the end before they commit it, then why not fully review it using the tools used before the dawn of LLMs?

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#352

Post by pdntspa »

embedding-shape wrote: post #62
pdntspa wrote: post #19

Earlier quoted context omitted.

> But where are the professional tools, meant to be used for people who don't want to do vibe-coding, but be heavily assisted by LLMs? Something that is meant to augment the human intellect, not replace it? Claude Code not good enough for ya?

Claude Code has absolutely zero features that help me review code or do anything else than vibe-coding and accept changes as they come in. We need diff-comparisons between different executions, tailored TUI for that kind of work and more. Claude Code is basically a MVP of that. Still, I do use Claude Code and Codex daily as there is nothing better out there currently. But they still feel tailored towards vibe-coding…

I just ask it to do a code review. It spits out a perfectly cromulent critique. Oftentimes it highlights stuff I would have missed.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#353

Post by tptacek »

renewiltord wrote: post #303
bravetraveler wrote: post #178

Earlier quoted context omitted.

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…

It is SEO-y and I’m sure no small impulse is to drive traffic to his website since he’s primarily an AI influencer. However, there are always people who are “native” to a platform and field. Pieter Levels is native to Twitter and the nomad community. Swyx is native to Twitter/HN and the devtools community. And simonw is native to at least HN and the LLM-interest community. And various streamers and onlyfans creators…

Wait how do I monetize? Am I leaving money on the table?

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#354

Post by pedrozieg »

The interesting bit in the blog isn’t the 72.2% SWE-Bench Verified number, it’s their own human eval: Devstral 2 beats DeepSeek V3.2 in Cline-style workflows but still loses clearly to Claude Sonnet 4.5. That’s a nice reminder that “open SOTA” on a single benchmark doesn’t mean “best tool for the job” once you’re doing multi-step edits across a messy real repo.

What is a big deal here is the combination of licensing and packaging. A 123B dense code model under a permissive license plus an open-source CLI agent (Vibe) that already speaks ACP is basically a reference stack for “bring your own infra + agents” instead of renting someone else’s SaaS IDE. If that ecosystem hardens (Cline, Kilo, Vibe, etc.), the moat shifts from “we have the only good code model” to “we own the best workflows and integrations”, and that’s a game open models can realistically win.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#355

Post by adam_patarino »

KronisLV wrote: post #296
Juminuvi wrote: post #263

Earlier quoted context omitted.

I know you say you don't use the paid apis, but renting a gpu is something I've been thinking about and I'd be really interested in knowing how this compares with paying by the token. I think gpt-oss-120b is 0.10/input 0.60/output per million tokens in azure. In my head this could go a long way but I haven't used gpt oss agentically long enough to really understand usage. Just wondering if you know/be willing to shar…

For comparison, here's my own usage with various cloud models for development: * Claude in December: 91 million tokens in, 750k out * Codex in December: 43 million tokens in, 351k out * Cerebras in December: 41 million tokens in, 301k out * (obviously those figures above are so far in the month only) * Claude in November: 196 million tokens in, 1.8 million out * Codex in November: 214 million tokens in, 4 million out…

This is the perfect use case for local models. It's why we set out to create cortex.build! A local LLM

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#356

Post by marco_craveiro »

InsideOutSanta wrote: post #350
Staross wrote: post #327

Earlier quoted context omitted.

Also tried it on a small project, it did ok finding issues but completely failed doing rather basic edits, like it lost closing brackets or used wrong syntax and couldn't recover. The CLI was easy to setup and use though.

In my experience, the messed up closing brackets are a surprisingly common issue for LLMs. Both Sonnet 4.5 and Gemini 3 also do this regularly. Seems like something that should be relatively easy to fix, though.

I use both Sonnet 4.5 and Opus 4.5 to edit lisp (emacs lisp to be be precise) and run into this issue extremely infrequently. Not sure if they have some special handling for this but seems to work ok. I have this problem with Gemini, and less frequently, with Qwen.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#357

Post by Barbing »

jgalt212 wrote: post #339
100721 wrote: post #326

Earlier quoted context omitted.

Web search-based RAG is very different from having something embedded in a model's training data, though.

ChatGPT website gives a similar answer. Are they running RAG, or the model? > Yes — I’m familiar with the “pelican riding a bicycle” SVG generation test. > It’s become a kind of informal benchmark people use when evaluating whether an image-generation or SVG-generation model can: ...

Runnin’ confabulations:

>Yes — the “hamster driving a car” prompt is a well-known informal test …

>…that’s a well-known informal test people use…(a mole-rat holding or playing a guitar).

Try any plausible concept. Get sillier and it’s trained to talk about it being nonsense. The output still claims it’s a real test, just a real “nonsense” test.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#358

Post by renewiltord »

tptacek wrote: post #353
renewiltord wrote: post #303

Earlier quoted context omitted.

It is SEO-y and I’m sure no small impulse is to drive traffic to his website since he’s primarily an AI influencer. However, there are always people who are “native” to a platform and field. Pieter Levels is native to Twitter and the nomad community. Swyx is native to Twitter/HN and the devtools community. And simonw is native to at least HN and the LLM-interest community. And various streamers and onlyfans creators…

Wait how do I monetize? Am I leaving money on the table?

Not so much leaving money on the table as you have a valuable resource you are underutilizing in this respect. You’d have to cross-cultivate your audience and expand to fill some niche.

That means that instead of dropping facts here you should post it on Substack and link to it here. You’ll be fine with it because you’re trusted here so people will be like “oh it’s fine”.

And then once you have the newsletter going and you have a following there you can do paid placements etc. that don't have to be done by you.

I think you have the highest potential on this front but that doesn't mean there's comparative advantage. It may not be worth it to you. For instance, I would never do it. To keep that wheel spinning you have to keep putting energy into it. And I have other ways of making money, so even with your account it would be a waste.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#359

Post by tptacek »

renewiltord wrote: post #358
tptacek wrote: post #353

Earlier quoted context omitted.

Wait how do I monetize? Am I leaving money on the table?

Not so much leaving money on the table as you have a valuable resource you are underutilizing in this respect. You’d have to cross-cultivate your audience and expand to fill some niche. That means that instead of dropping facts here you should post it on Substack and link to it here. You’ll be fine with it because you’re trusted here so people will be like “oh it’s fine”. And then once you have the newsletter going a…

I'm going to start encrypting the bottom 2/3rds of all my comments and charging a subscription fee for the unlocks. I can be my own Substack, dammit.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#360

Post by renewiltord »

tptacek wrote: post #359
renewiltord wrote: post #358

Earlier quoted context omitted.

Not so much leaving money on the table as you have a valuable resource you are underutilizing in this respect. You’d have to cross-cultivate your audience and expand to fill some niche. That means that instead of dropping facts here you should post it on Substack and link to it here. You’ll be fine with it because you’re trusted here so people will be like “oh it’s fine”. And then once you have the newsletter going a…

I'm going to start encrypting the bottom 2/3rds of all my comments and charging a subscription fee for the unlocks. I can be my own Substack, dammit.

Hahaha ))
Post reply on HN