247 karma · joined June 30, 2026
I will see where Chonk is better though, since you have both options in one subscription.
Since cost is so much higher than deepseek though it really seems like the biggest reason to use it would be "in the mistral subscription" for personal use or "because you need to abide by european data privacy laws" for companies.
Mostly I'm happy they're still in competition, as I mentioned already elsewhere.
But you're right, Mistral Large 4 seems a much more expensive but overall weaker model across the board.
The reason to use them would be, well, because they're...Mistral. They're in EU, france is large in nuclear energy so the energy cost of training has much less of an environmental impact, the data protection laws are very good in EU. This can really be a deciding factor for many EU companies, and I think it's good that they now have something which is at least semi-usable. (apparently)
It's also good that other options exist, even if they are worse. Deepseek is kind of like a large specter looming over every model release, because it's just SO cheap and good. That doesn't mean we should abandon every other model.
Still, the model is not really competitive on price and abilities alone. I'm mostly happy to see Mistral still in the fight.
I don't use Anthropic products at all, so I was not really sure myself but apart from the models they pretty much only have Claude Code afaik.
And now they're publishing a blog post about writing their own vcs because they have 30000 commits a day. For what? Isn't Claude still based on react?
Do they need this many commits just for claude? Or is that about the model, do they develop that much extra internal tooling?
I admit it is very much possible I am wrong, but without further information this seems a bit like a red flag to me.
On top of that, it also feels very much like a normal CLI tool, which is a big plus for me.
It does not support plugins or MCP, which could both be a big negative for many people, but for now I was able to find a good terminal alternative for everything I needed.
Just a huge recommendation from my side as well, not affiliated in any way myself.
The capabilities of all models increasing so much all the time means there are simply less and less tasks you need a frontier model for.
Even if Opus 5.5 is 500x better than Deepseek, if deepseek can solve all my problems, why do I need to pay for more?
I am always on the lookout to automatate as much boring, everyday tasks. A Smart Fridge like that would allow you to generate shopping lists and reduce food waste by alerting you to possible soon-to-be-spoiled food.
A bit like what roombas are doing for cleaning. You still need to do it yourself a bit, but they help.
Not necessary, not even a gamechanger but another neat home automation. Would be nice, sad to hear they don't work well.
I don't think this brings your point across at all. If you disagree with the article, just saying "no, it's a tool, like coffee" does not meaningfully engage at all with any of the points made.
Because I feel that the technology and space is - so - hyped and fast moving that a lot of cultish feeling rituals seem to pop up, none of which are backed by evidence. Anthropic openly recommend giving the agents.md file an architectural overview of the code, and the one time this was studied they found the opposite - that the agents.md file is best for concrete commands about how to build stuff and such, and - not - huge overviews. This was, and still is, the official recommendation from Anthropic as far as I can tell.
And then there are the benchmarks, how feel vague and not concrete, and everyone kind of knows they're not the best cuz you can't just assign these tools one fixed number ( for multiple reasons ), but everyone still looks at them and compares them.
People share skills and superpowers and plugins and mcps and very, very few of them have and kind of proof they do much at all.
It all feels a bit weird to me, and I've been on the lookout for exactly these kinds of studies more lately, because I think having this research, even if not done on the exact newest models or not the exact, newest thing, are still - vastly - superior to the alternative.
And there might be a point to these arguments, vaguely. However:
There never seems to be - any - kind of counter example or reasoning behind the rationale. You have an in depth and empirical study, done by researchers who, frankly, now their shit (most of the time)
And on the other hand a random internet comment saying "nope" because...the models aren't the latest.
If the latest models really would make a difference, you should at least provide some kind of evidence towards that. As it stands though, every time these comments come up this is missing.
There seems to just be a vaguely defined understanding that "everything changes all the time, and nothing you ever research is transferable to state-of-the-art models"
Which brings me to my second point about these kinds of arguments:
LLM models often - aren't - fundamentally different. Yes, they are vastly more capable. And yes, there are emergent properties. But at their core, they function very much similarly. And for quite a while now, there have not been any of these drastic changes we saw when LLMs first become "good enough" for agentic coding.
I am tired of dismissing empirical evidence and studies every. single. time for reasons without evidence and seemingly a vague sense of "no, but my model is different"
I assume the limit for me is memory bandwith, as the 7900 XTX has the same bandwith as the 3090 from what I can gather and I already reached ~60 t/s with Unsloth. Those would fit with the numbers Byteshape has for their cards.
4090 and 5090 have much higher bandwith apparently, so on those cards you can probably get much more out of the kinds of performance improvements they are doing.
As long as the model you're using solves the problems you have to your satisfaction, there is no need to try any other models, except for financial reasons maybe.
So I start with a relatively cheap model (GLM 5.3 flash for me) and as long as it accomplishes the task (it did so far) I don't have to change. And even if it can't do something, the first thing I change is see if I can give it more tools or better context (useful even if I switch models later) or trying a different approach to the problem.
If google/gemma-4-31b works, you don't need to overthink it.
But keep in mind this is a report from OpenAI about OpenAI, who have a financial incentive to present this in a certain light. Take these things with a grain of salt.
This does not mean that models are now self-aware.
So the points about it being a well behaved unix tool, installing it via brew and it not being react are points I - love - to see.
Thank you for making it, I will definitely try it out.
Seriously "thought to be" is such a baseless statement. Thought to be by whom? And on what basis?
The core of the argument as I understood it is that LLMs aren't just using existing data is training but also new ones. That's fine and good, and you can't simply assume an LLM is simply mashing together all it's data to give you an average of all that got fed into it - but at least I would still call it a "next token predictor"
It's not using just training data, but what it's doing is predicting the next token to get to the solution. As far as my amateur knowledge goes, LLMs still roughly go token by token, deciding which one fits best given the context.
It's just not predicting based on it's training data, but predicting based on RLVR & more, trying to get to the optimal solution ( as much as the solutions CAN be optimal)
And I honestly think keeping this very much in mind is helpful in understanding and dealing with LLMs.
This is fair to say if someones last experience with AI was copy-pasting code into GPT3 chat windows years ago, but Deepseek is a more than capabale model and enough for someone to get an informed opinion about the technology.
If people have actual counter argument, use those. And if some of those counter argument are "What you say isn't possible, the neweste model can do and here are examples of that", that is fine.
But a blanket "Nuh-uh, it wasn't Model X" is not only a poor argument but also automatically invalidates any criticism when a new, better model comes out - and that can't be the basis of a good argument.
You are absolutely right that there is a physical limit about these things, but very often I find that the solution is a clever way to work around the problem. Maybe the problem with knowledge of the models will be improved by them looking the information up in a better way - so smaller models will not have to have the knowledge trained in but will default to checking. Maybe Models will, I dunno, focus on training in assembler and start to only ever check the compiled output so they only ever need to learn assembler and will then compile the solution to reason about the assembler code.
Obviously that last part is a ridiculous example because I'm not gonna be able to come up with a solution myself - I'm not nearly smart enough for that. But I h ope you get what I mean. Not going the direct route but instead finding solutions people didn't think of before.
Regarding appImage or rpm, attackers need to build and package these to inject these, while this curl | bash pipe opens up the possiblity of payloads simply by taking over the domain. And this isn't really that far fetched, just think about the Notepad++ update payload recently. The regular package was unaffected while the domain used for the update was taken over.
Then theres also the argument about normalization. Just like he said, this isn't just something he said, this is a very real argument. You don't want to teach users bad habits. Even if / you / inspect the code you get, not everyone will. And ultimately, we should strive to make the Internet a safer place, if only to get less botnets.
They also recommend starting with an /init command, which is also something the study very specifically called out as "having a marginal negative effect"
And from personal experience, I can only confirm that many people seem to see this as the main purpose of agents/claude md files - a persistent architectural overview of your project.
Quick Edit: My point simply being that I think it's understandable if some people don't understand the big deal about these files because they've had a drastically different experience than other people - anthropic themselves recommend apparently totally ineffective practices on their website, and the starter tool present in many harnesses seems to even have a (marginal) negative effect.
Most of the agents.md and what people use it for / write into is does, in fact, not make a difference.
Now, sure, this study is a bit old for LLM standards - as everything beyond the current month is - but
a) I haven't seen any tangible evidence to the contrary and
b) Since the basic inner workings of LLMs haven't changed I'd be sceptical of this not still applying.
I think one major side effect of LLMs moving so fast is that best practices and how to use this tool is very much not catching up as fast.
No one knows what is best and what actually makes a difference, doubly so because LLMs are / very / hard to quantify - even benchmarks themselves are very rough estimations.
People do, in fact, use stuff which makes no difference all the times.
Currently I very much can't decide between going for a bit of a lower Q4 Quant to squeeze out a bit of buffer and ctx or wondering if a slightly higher (IQ4_XS vs Q4_K_M/XL) is worth it
Quick Edit: Since github is back up, heres the comment I was referencing: https://github.com/earendil-works/pi/issues/534#issuecomment...
The ticket is closed and this will not be changed, period.
If I don't find anything which fits me I might fork it, but even that little effort is not really worth it if theres something which fits me better.
I already found maki which...seems to do the exact same job pi did for me, and I wanna check out crush as well.
As many advantages as pi has in some areas, there are definitely areas where I believe the hype to be a bit overstated. While the config folder is, ultimately, not relevant for performance, how this was and is continued to handled is a bit frustrating for me.
They have made it abundantly clear it's not going to change however so I'm looking at how other coding agents perform currently.
I'm asking because I personally only use AI with specific and detailed instructions, building my projects piece-by-piece.
I mostly don't look at the low level code and some of it I don't understand as much as I'd like, but I very much give much more technical instructions than a simple, two sentence prompt.
So, it seems to me this "oneshot from a simple prompt" eval is fairly meaningless when it comes to model evaluation itself, as it is in no way representative of real world application.
This would be more something for "vibe coders", people with little to no programming background wanting a website?
Maybe you're right in the fact that the coping mechanism help with that. Maybe using LLMs is similar in that it is easy to lose focus for neurotypicals so having lived with that we know how to handle it. Or maybe it's just us, who knows.