Product Launch
anonymous
728 points
337 comments
Posted24 days agoActive18 days ago
Mistral
mistral.ailauncheddeveloper_tooldevelopers
Key Features
Devstral2 model releaseMistral Vibe CLI tool
Tech Stack
Mistral modelsCLI
Key Features
Tech Stack
Not sure you've kept up to date, US have turned their backs on most allies so far including Europe and the EU, and now welcome previous enemies with open arms.
They did.
- https://helsing.ai/newsroom/helsing-and-mistral-announce-str... - https://sifted.eu/articles/mistral-helsing-defence-ai-action... - Luxembourg army chose Mistral: https://www.forcesoperations.com/la-pepite-francaise-mistral... - French army: https://www.defense.gouv.fr/actualites/ia-defense-sebastien-...
And while it may miss the HN crowd, one of the main selling-points of AI coding is the ease and playfulness.
If you're actually making sure it's legit, it's not vibe coding anymore. It's just... Backseat Coding? ;)
There's a level below that I call Power Coding (like power armor) where you're using a very fast model interactively to make many very small edits. So you're still doing the conceptual work of programming, but outsourcing the plumbing (LLM handles details of syntax and stdlib).
sorry to disappoint you but that is also been considered vibecoding. It is just not pejorative.
Imo, if you read the code, it's no longer vibecoding.
Also, we’re both “people in tech”, we know LLMs can’t conceptualise beyond finding the closest collection of tokens rhyming with your prompt/code. Doesn’t mean it’s good or even correct. So that’s why it’s vibe coding.
Maybe common usage is shifting, but Karpathy's "vibe coding" was definitely meant to be a never look at the code, just feel the AI vibes thing.
Even the Gemini 3 announcement page had some bit like "best model for vibe coding".
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 professional work where you need tight control over the quality, you can obviously not vibe your way to excellency, hard reviews are required, so not "vibe coding" which is all about unreviewed code and just going with whatever the LLM outputs.
But regardless of that, it seems like everyone and their mother is aiming to fuel the vibe coding frenzy. 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? All the agents seem to focus on off-handing work to vibe-coding agents, while what I want is something even tighter integrated with my tools so I can continue delivering high quality code I know and control. Where are those tools? None of the existing coding agents apparently aim for this...
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 can integrate with your IDE through the watch mode. It's somewhat crude but still useful way. But I find myself more often than not just running Aider in a terminal under the code editor window and chatting with it about what's in the window.
> The chat interface
Seems very much not, if it's still a chat interface :) Figuring out a chat UX is easy compared to something that was creating with letting LLM fill in some parts from the beginning. I guess I'm searching for something with a different paradigm than just "chat + $Something".
It's all very fluffy and theoretical of course.
"I want you to do feature X. Analyse the code for me and make suggestions how to implement this feature."
Then it will go off and work for a while and typically come back after a bit with some suggestions. Then iterate on those if needed and end with.
"Ok. Now take these decided upon ideas and create a plan for how to implement. And create new tests where appropriate."
Then it will go off and come back with a plan for what to do. And then you send it off with.
"Ok, start implementing."
So sure. You probably can work on this to make it easier to use than with a CLI chat. It would likely be less like an IDE and more like a planning tool you'd use with human colleagues though.
So you'd write a function name and then tell it to flesh it out.
function factorial(n) // Implement this. AI!
function factorial(n) {
if (n === 0 || n === 1) {
return 1;
} else {
return n \* factorial(n - 1);
}
}
I'm really curious to try Mistral's vibe, but even though I'm a big fanboi I don't want to be tied to just one model. Aider lets tier your models such that your big, expensive model can do all the thinking and then stuff like code reviews can run through a smaller model. It's a pretty capable tool
Edit: Fix formatting
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.
If you babysit every interaction, rather than reviewing a completed unit of work of some size, you're wasting your time second-guessing that the model won't "recover" from stupid mistakes. Sometimes that's right, but more often than not it corrects itself faster than you can.
And so it's far more effective to interact with it far more async, where the UI is more for figuring out what it did if something doesn't seem right, than for working live. I have Claude writing a game engine in another window right now, while writing this, and I have no interest in reviewing every little change, because I know the finished change will look nothing like the initial draft (it did just start the demo game right now, though, and it's getting there). So I review no smaller units of change than 30m-1h, often it will be hours, sometimes days, between each time I review the output, when working on something well specified.
This is exactly the CLI I'm referring to, whose name implies it's for playing around with "vibe-coding", instead of helping professional developers produce high quality code. It's the opposite of what I and many others are looking for.
Claude Code not good enough for ya?
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 instead of professional development.
Trying to follow along better is exactly the opposite of what I'd advocate - it's a waste of time especially with Claude, as Claude tends to favour trying lots of things, seeing what works, and revising its approach multiple times for complex tasks. If you follow along every step, you'll be tearing your hair out over stupid choices that it'll undo within seconds if you just let it work.
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".
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.
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.
Err, doesn’t it have /review?
What kind of hardware do you have to be able to run a performant GPT-OSS-120b locally?
There are many platforms out there that can run it decently.
AMD strix halo, Mac platforms. Two (or three without extra ram) of the new AMD AI Pro R9700 (32GB of RAM, $1200), multi consumer gpu setups, etc.
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.
"There is nothing more permanent than a temporary demo"
But there is nothing more permanent that a quickly hacked together prototype or personal productivity hack that works. There are so many Python (or Perl or Visual Basic) scripts or Excel spreadsheets - created by people who have never been "developers" - which solve in-the-trenches pain points and become indispensable in exactly the way _that_ xkcd shows.
What matters is high quality specifications including test cases
Says the person who will find themselves unable to change the software even in the slightest way without having to large refactors across everything at the same time.
High quality code matters more than ever, would be my argument. The second you let the LLM sneak in some quick hack/patch instead of correctly solving the problem, is the second you invite it to continue doing that always.
I have a feeling this will only supercharge the long established industry practice of new devs or engineering leadership getting recruited and immediately criticising the entire existing tech stack, and pushing for (and often succeeding) a ground up rewrite in language/framework de jour. This is hilariously common in web work, particularly front end web work. I suspect there are industry sectors that're well protected from this, I doubt people writing firmware for fuel injection and engine management systems suffer too much from this, the Javascript/Nodejs/NPM scourge _probably_ hasn't hit the PowerPC or 68K embedded device programming workflow. Yet...
In my mind, it's somewhat orthogonal to code quality.
Waterfall has always been about "high quality specifications" written by people who never see any code, much less write it. Agile make specs and code quality somewhat related, but in at least some ways probably drives lower quality code in the pursuit of meeting sprint deadlines and producing testable artefacts at the expense of thoroughness/correctness/quality.
While True:
0. Context injected automatically. (My repos are small.)
1. I describe a change.
2. LLM proposes a code edit. (Can edit multiple files simultaneously. Only one LLM call required :)
3. I accept/reject the edit.
This is what we're building at Brokk: https://brokk.ai/
Quick intro: https://blog.brokk.ai/introducing-lutz-mode/
The only thing I found is a pay-as-you-go API, but I wonder if it is any good (and cost-effective) vs Claude et al.
With pricing so low I don't see any reason why someone would buy sub for 200 EUR. These days those subs are so much limited in Claude Code or Cursor than it used to be (or used to unlimited). Better pay-as-you-go especially when there are days when you probably use AI less or not at all (weekends/holidays etc.) as long as those credits don't expire.
As long as it doesn't mean 10x worse performance, that's a good selling point.
In work, where my employer pays for it, Haiku tends to be the workhorse with Sonnet or Opus when I see it flailing. On my own budget I’m a lot more cost conscious, so Haiku actually ends up being “the fancy model” and minimax m2 the “dumb model”.
Uh, the "Modified MIT license" here[0] for Devstral 2 doesn't look particularly permissively licensed (or open-source):
> 2. You are not authorized to exercise any rights under this license if the global consolidated monthly revenue of your company (or that of your employer) exceeds $20 million (or its equivalent in another currency) for the preceding month. This restriction in (b) applies to the Model and any derivatives, modifications, or combined works based on it, whether provided by Mistral AI or by a third party. You may contact Mistral AI (sales@mistral.ai) to request a commercial license, which Mistral AI may grant you at its sole discretion, or choose to use the Model on Mistral AI's hosted services available at https://mistral.ai/.
[0] https://huggingface.co/mistralai/Devstral-2-123B-Instruct-25...
Whenever anybody tries to claim that a non-commercial licenses is open-source, it always gets complaints that it is not open-source. This particular word hasn’t been watered down by misuse like so many others.
There is no commonly-accepted definition of open-source that allows commercial restrictions. You do not get to make up your own meaning for words that differs from how other people use it. Open-source does not have commercial restrictions by definition.
The term "open-source" exists for the purposes of a particular movement. If you are "for" the misuse and abuse of the term, you not only aren't part of that movement, but you are ignorant about it and fail to understand it— which means you frankly have no place speaking about the meanings of its terminology.
People can also say 2+2=5, and they're wrong. And people will continue to call them out on it. And we will keep doing so, because stopping lets people move the Overton window and try to get away with even more.
And whenever they do so, this pointless argument will happen. Again, and again, and again. Because that’s not what the word means and your desired redefinition has been consistently and continuously rejected over and over again for decades.
What do you gain from misusing this term? The only thing it does is make you look dishonest and start arguments.
This kind of thing is how people try to shift the Overton window. No.
If you want to use something, and your company makes $240,000,000 in annual revenue, you should probably pay for it.
"Open Source" is nebulous. It reasonably works here, for better or worse.
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, etc.
No it isn't it is well defined. The only people who find it "nebulous" are people who want the benefits without upholding the obligations.
well we don't really want to open that can of worms though, do we?
I don't agree with ceding technical terms to the rest of the world. I'm increasingly told we need to stop calling cancer detection AI "AI" or "ML" because it is not the 'bad AI' and confuses people.
I guess I'm okay with being intransigent.
As someone who was born and raised on FOSS, and still mostly employed to work on FOSS, I disagree.
Open source is what it is today because it's built by people with a spine who stand tall for their ideals even if it means less money, less industry recognition, lots of unglorious work and lots of other negatives.
It's not purist to believe that what built open source so far should remain open source, and not wanting to dilute that ecosystem with things that aren't open source, yet call themselves open source.
Because instead of making the point "this license isn't as permissive as it could/should be" (easy to understand), instead the point being made is "this isn't real open source", which comes across to most people as just some weird gate-keeping, No True Scotsman kinda thing.
Though given the stance you are taking in this conversation, I'm not surprised you want to quibble over that.
¯\_(ツ)_/¯
With all due respect, don't you see the irony in saying "people with a spine who stand tall for their ideals", and then arguing that attaching "restrictions" which only affect the richest megacorporations in the world somehow makes the license not permissive anymore?
What ideals are those exactly? So that megacorporations have the right to use the software without restrictions? And why should we care about that?
Anyone can use the code for whatever purpose they want, in any way they want. I've never been a "rich megacorporation", but I have gone from having zero money to having enough money, and I still think the very same thing about the code I myself release as I did from the beginning, it should be free to be used by anyone, for any purpose.
> if what you are talking about is the license, call it "open license".
If you want to build something proprietary, call it something else. "Open Source" is taken.
Whatever name they come up with for a new license will be less useful, because I'll have to figure out that this is what that is
I do not mind having a license like that, my gripe is with using the terms "permissive" and "open source" like that because such use dilutes them. I cannot think of any reason to do that aside from trying to dilute the term (especially when some laws, like the EU AI Act, are less restrictive when it comes to open source AIs specifically).
Good. In this case, let it be diluted! These extra "restrictions" don't affect normal people at all, and won't even affect any small/medium businesses. I couldn't care less that the term is "diluted" and that makes it harder for those poor, poor megacorporations. They swim in money already, they can deal with it.
We can discuss the exact threshold, but as long as these "restrictions" are so extreme that they only affect huge megacorporations, this is still "permissive" in my book. I will gladly die on this hill.
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.
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 people, but instead for the interest of the megacorps.
As soon as there is even the tiniest of restrictions, one which doesn't affect anyone besides a bunch of richiest corporations in the world, a bunch of people immediately come out of the woodwork, shout "but it's not open source!" and start bullying everyone else to change their language. Because if you even so much as inconvenience a megacorporation even a little bit it's not Open Source (TM) anymore.
If we're talking about ideals then this is something I find unsettling and dystopian.
I hard disagree with your "It also makes life harder for individuals and small companies" statement. It's the opposite. It gives them a competitive advantage vs megacorps.
> 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.
Yes, they do, and the only reason for using the term “open source” for things whose licensing terms flagrantly defy the Open Source definition is to falsely sell the idea that using the code carries the benefits that are tied to the combination of features that are in the definition and which are lost with only a subset of those features. The freedom to use the software in commercial services is particularly important to end-users that are not interested in running their own services as a guarantee against lock-in and of whatever longevity they are able to pay to have provided even if the original creator later has interests that conflict with offering the software as a commercial service.
If this deception wasn't important, there would be no incentive not to use the more honest “source available for limited uses” description.
(Surely they won't release it like that, right..?)
That looks like the next flagship rather than the fast distillation, but thanks for sharing.
Google should be punishing these sites but presumably it's too narrow of a problem for them to care.
177 more comments available on Hacker News
Not affiliated with Hacker News or Y Combinator. We simply enrich the public API with analytics.