> So many comments here missing the big picture, and just gleefully pointing out that Anthropic got what they deserved, or that this is the natural culmination of some kind of marketing stunt.
They are not wrong, it feels like that Game of Thrones season where someone thought it would be a great idea to let the fanatics re-arm.
> The real story here is that this may be the beginning of governments restricting the availability of strong LLMs to the public, to you. Fable was the strongest model on the market, and the US government has told you you can’t use it (technically, only if you’re not a US citizen, but in practice, even if you are). If you think the solution here is going to be open source Chinese models and / or running on your own hardware, think again. Do you think China is going to allow the strongest LLMs from companies within its borders to be open source a year from now when they have Mythos capabilities, if the US government is keeping the strongest American models back? Unlikely. These are heading in the direction of being powerful cybersecurity weapons and it will be in the interest of nation states to restrict and control them. In 2 years time, I would be surprised if the strongest LLMs are available for general use at all.
The world is a bit bigger than US and China, if Anthropic did it, another company can do it as well.
I am highly skeptical about Mythos's part in the whole cyber security angle and Anthropic seems to agree with me:
> We have reviewed a report that we believe is the basis of the government's directive and validated that the level of capability displayed there is widely available from other models (including OpenAI’s GPT-5.5)
It does sound funny to hear this from Anthropic after they spent recent months with scaremongering about Mythos's capabilities, now they say it was a prank bro, you can actually achieve more or less the same with good old GPT-5.5.
> Will we be the poorer for that, or will we be safer? I think poorer, because I hate being told what technology I can and can’t use, but I’m not certain. Maybe you think the government should restrict strong LLMs. Maybe you don’t. But either way, this is big news and a rubicon has been crossed and a precedent set. That’s true even if the motivation for this is just the government settling scores with Anthropic.
What this has demonstrated: if you can't run the software on your own hardware, you should assume that it can be taken away at any moment.
At this point I'm starting to get scared that the hardware itself could get banned. We went from free personal computing to remote attestation to being priced out and now the threat of being literally regulated looms over us. Even if we amassed a small fortune and decided to spend it on our own inference-capable computers, we might find that we literally can't purchase the hardware.
You can’t just buy H100 there are government limits on that.
RTX4090 maybe has no government limits but NVidia is definitely limiting bulk orders per retailer. I guess if you buy a lot from each retailer you will most likely get flagged in one way or the other.
Unfortunately Mistral is not close to the frontier. Their last release Mistral Medium 3.5 128B is near the performance[0] of QWEN-3.6-27B, a much smaller model that was released earlier.
It's good that they exist, and I hope they catch up, but if you don't have origin constraints for your use case I don't see why you would chose their models today.
[0]: On the only benchmark they both published performance results - SWE-bench Verified -they are within a margin of error Mistral 77.6 vs Qwen 77.2.
Within Spec Driven Development style coding for me Claude Sonnet 4.5 was the game changer and Mistral is I believe at that level already. GLM is allegedly also on par with even some of the Opus models, so if the US vendors would vanish tomorrow, there would be alternatives. Would I miss Opus 4.8 and the Claude Code harness? of course I would! But the world wouldn't stop.
What I am trying to get at is that the frontier is great, but you can be fine with less as well.
I'm a European, the EU is supposed to be one of the closest allies of the US.
The US government found a jailbreak that allowed the user to make Fable do bad things, this is so dangerous that this model must be held back in areas that are not the US...
If this is so dangerous why allow US nationals access to it? Are there no evil people in the US?
Going back to my perspective: let's say I control a big enterprise or a government body, how should I view this or US technology? Should I be like: yes, let's use US tech, they are a reliable partner and would never abruptly cut us off! Or should I be like: there are competent alternatives out there and if your work hinges on wether or not you had access to Fable 5, then your business is probably not going to survive for long.
Back when Snowden leaked all of the spying information, the only thing the States cared about was whether they spied on their own citizens. The fact that they spied on the citizens of their allies, including yes, the EU, barely made the news.
I don't think it makes sense the assume the US considers any country its ally.
sorry that's what I meant: I remember watching their depositions or whatever they were called, and their only concern was whether or not they had spied on US citizens. Whether or not they spied on their allies, I do not recall any coverage of from their primary news outlets (or inside their depositions) at all.
I agree with the sentiment and dislike Kissinger, but that quote is always paraphrased and out of context.
The full quote makes it clear Kissinger was saying, in the context of the Vietnam War, that the US should come to the aid of their friends:
> "Word should be gotten to Nixon that if Thieu meets the same fate as Diem, the word will go out to the nations of the world that it may be dangerous to be America's enemy, but to be America's friend is fatal."
I'm well aware of its context and original meaning, and I'm very happy to twist its meaning into something Kissinger would disagree with any chance I get.
It shares that intelligence with the countries it was gathered from. It's been explicitly stated many times that this is an intentional work around for weak constitutional provisions on protection of citizens.
I spy on your guys. You spy on mine. We all share notes.
This isn't a "The US vs. The World" this is "The Wealthy vs. The Poor."
It would be a game changer as it would allow working with highly sensitive data, I'm surprised Apple didn't think of doing something like that, a private server that could know everything about me and my business sounds thrilling.
Pretty much described what MSFT is trying to do with M365 Copilot. It's "secure", it can be deployed in GCC tenants, etc. It may not be a dedicated private server exactly, but they believe it is private enough.
I don't think there is anything private about that, what I was actually thinking is the polished equivalent of me spinning up LM Studio (or Ollama...) and rolling my own vector database. Mandatory updates and phoning home are a no-go, I just want it to run on my private network the same way my NAS does.
> I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckless to give agents full access to your machine, and keep doing it anyway.
What if you have two machines and the one you give to the agent is constantly backed up?
They cut prices and get more customers who are going to move to the next vendor that cuts prices even more or when they jack up the prices again.
I am not complaining, I like my investor subsidised tokens, I don't see what these companies see as their end goal when it's becoming more and more possible to run a competent LLM locally(even with today's RAM prices).
I am surprised that there is no Claude or ChatGPT machine that I could buy, I feel like they should be opening up that model, but I guess subscriptions look better on balance sheets.
> Sure, humans should steer the agent to prevent spaghetti codebases with circular dependency graphs. We don't want F-rated codebases that are impossible to touch without breaking something. But a C or D? It's now fine. Nobody needs A or B-grade codebases anymore because they're being made for LLMs, not for humans to read.
Your job is now to get the LLMs to write good code the same way you would do it if instead of AI agents, you would be leading a team of humans.
They are not wrong, it feels like that Game of Thrones season where someone thought it would be a great idea to let the fanatics re-arm.
> The real story here is that this may be the beginning of governments restricting the availability of strong LLMs to the public, to you. Fable was the strongest model on the market, and the US government has told you you can’t use it (technically, only if you’re not a US citizen, but in practice, even if you are). If you think the solution here is going to be open source Chinese models and / or running on your own hardware, think again. Do you think China is going to allow the strongest LLMs from companies within its borders to be open source a year from now when they have Mythos capabilities, if the US government is keeping the strongest American models back? Unlikely. These are heading in the direction of being powerful cybersecurity weapons and it will be in the interest of nation states to restrict and control them. In 2 years time, I would be surprised if the strongest LLMs are available for general use at all.
The world is a bit bigger than US and China, if Anthropic did it, another company can do it as well.
I am highly skeptical about Mythos's part in the whole cyber security angle and Anthropic seems to agree with me:
> We have reviewed a report that we believe is the basis of the government's directive and validated that the level of capability displayed there is widely available from other models (including OpenAI’s GPT-5.5)
It does sound funny to hear this from Anthropic after they spent recent months with scaremongering about Mythos's capabilities, now they say it was a prank bro, you can actually achieve more or less the same with good old GPT-5.5.
> Will we be the poorer for that, or will we be safer? I think poorer, because I hate being told what technology I can and can’t use, but I’m not certain. Maybe you think the government should restrict strong LLMs. Maybe you don’t. But either way, this is big news and a rubicon has been crossed and a precedent set. That’s true even if the motivation for this is just the government settling scores with Anthropic.
What this has demonstrated: if you can't run the software on your own hardware, you should assume that it can be taken away at any moment.
reply