Like it basically jail broke the "no security vul guard rails" not in any clever way but just by fixing them, producing exploit code just by writing test cases making sure it's fixed. So you just need to look at the code & tests as a human to get vulnerabilities and exploits(components).
What makes this so beautiful IMHO is that it's a trivial jail break, but also a close to unfixable. At least not without making the model close to useless for normal development (it refuses to fix bugs/write code) or making it a major liability (it silently pretends it didn't see bugs and silently avoids fixing it, which for a human would count as intentional sabotage and might involve criminal liability).
What's surprising to me is that anyone who has a CS education thinking that jailbreaks are not trivial. It is as simple as normal algorithmic reduction [1], e.g can I transform a dangerous task into a not-dangerous task that the LLM will agree to solve, and then re-transform back.
Something being possible doesn't mean it's easy. Transforming a problem from a forbidden shape into an allowed shape could well be harder than just solving the original problem.
The movie M3GAN 2.0 had the exact same plot twist. The kid in the movie even explains outloud what the bot had to do to deal with the limitation. So in other words, since 2025, even teens know this "sandboxing the LLM by layering prompts" thing is never going to work.
The article does not state at any point that the written test cases involved actual exploit code, and this is also very unlikely given what we know about Fable. Even if they did, it would not in any way be exposing the ability that originally raised concern wrt. Mythos Preview, viz. staging realistic cyber attacks that would be able to work around non-trivial defenses and chain vulnerabilities in a goal-directed way.
Opus can very much "fix the code". Quite possibly even Sonnet can. This is a big fat nothingburger and it's increasingly looking like the political restriction of Fable at least (not Mythos itself, of course) was arbitrary and based on the flimsiest pretext.
Ok, and how is that determined? How does anthropic know my "kernel" project isn't a personal toy and not the Linux kernel? How does anthropic determine I'm a legitimate kernel hacker? What proof do I give them and how does it tie back to my email? What would the steps be to create a new project? Do I need to send anthropic a list of my team members each time and keep them updated as the company changes? Shall I be giving them access to our company's active directory?
> A subsequent investigation found that the campaign to insert the backdoor into the XZ Utils project was a culmination of over two years of effort, starting in 2021, by a user going by the name "Jia Tan". They used sock puppetry in a pressure campaign against the original maintainer of XZ Utils, eventually being given maintainer permissions on the project.
Can we retire the “seatbelts are useless because they can’t prevent every loss of life” approach to risk mitigation please?
If the acceptance criteria is “would prevent every single past instance and every imaginable future instance”, then yes, no mitigation is every sufficient to address any problem in the world, so we might as well give up.
They weren't freaked by anything, it's a retaliatory shakedown after ideological differences and Anthropic not doing exactly what they're told/what the Admin wants them to do.
they're setting the scene for an attempt to scare the geriatric decision makers into banning free and open source ML, as it's the industry's only real competition
If you set aside political menace, this is a huge problem with Anthropic's strategy.
You _cannot_ say that Mythos is super dangerous and can only be rolled out to certain people, but then release Fable with anything other than bulletproof cyber denials.
Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work.
So you've ended up in a situation where Anthropic are simultaneously claiming it's a incredibly dangerous model _and_ there are (minor, potentially) problems with the security "protections".
As technical people we understand that nothing can be perfect, esp in LLM world. But all my non technical friends were really confused how they had managed to make the model "safe" so quickly when it was released and the general sentiment was it shouldn't have been released - and now to an outsider I think it looks like it was never safe at all to release, so I can totally see how the current US administration have got themselves very upset with it.
_Even if_ there was no political bad will, it's a bit of a silly scenario to end up in, and really quite easily foreseen.
> Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work.
As a scientist who repeatedly ran into the classifier-based denials: it appears Anthropic’s strategy to make denials more robust, at the cost of many false positives, was to have a separate classifier processing both input and output tokens, at an extremely simple, almost keyword-search level. One weakness of this approach is that it only catches things that use the right keywords: it is in some sense weak exactly where an LLM-based classifier would be stronger.
Work on abstract, closer-to-CS algorithms that used chemistry terminology were blocked immediately, while work directly relevant to chemistry/biology experiments, writing code to process images from a very specific microscopy setup relevant primarily to biological samples, was never blocked at all, because it happened to never use relevant keywords.
That’s consistent with this situation: finding and fixing bugs in the context of looking for bugs perhaps happened to never use words like ‘exploit’ or ‘cybersecurity’.
> Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work
Exactly. AI safety is nonsensical. You cannot define the set of "bad strings". The billion monkeys with typewriters are eventually going to be able to produce them. Any "safety" system for constraining LLM output is going to have a nonzero leak rate.
But on the other hand, this is also irrelevant, unless you're irresponsible enough to connect an LLM to something that actually matters.
Yes, it's going to alarmingly accelerate vulnerability finding. But, as we know from decades of security research, that's a three way problem already between the devs, the black hats, and the white hats.
Let's not pretend the strategy of "the US will always have a technological advantage and veto over China" will work either.
I get that, but anyone else releasing a model of similar capabilities has the advantage that they haven't spent the last few months hyping the danger up to fever pitch.
Oh, don’t worry. Once Fairytale 5 is back online, Anthropic will crank the fever machine to a new high setting. It won’t have anything to do with their IPO - just their sincere desire to help humanity by selling deadly artifacts and wringing their hands.
that won't be leaked, because then we'd know what vulnerabilties they don't want patched that they are so willing to go as far as fuck over the worlds leading company in the worlds most important industry
Isn’t the inverse of this “hack” really difficult to bypass still? They have the model some code they knew had certain security flaws and it fixed them with the right prompt. It seems this type of jailbreak requires that you already know a desired end state, rather than relying on the model to do the heavy creative lift work. Perhaps I’m just not being imaginative enough on the prompt side here though.
Did they try other publicly available models on the same code with the same prompts before the ban? Was Fable the only one which was able to detect and fix the security vulnerabilities?
So, basically the model didn't agree to expose possible vulnerabilities but agree to patch those?
Regardless of the request to take Fable 5 down.
Why is requesting the model to show vulnerabilities is being blocked if fixing it not? is it based on the assumption of the intention?
I don't quite get the benefit of limiting it. So if anyone can explain it better it'll be appreciated.
> Why is requesting the model to show vulnerabilities is being blocked if fixing it not?
This is how Anthropic describes Fable's behavior:
"When Fable’s classifiers detect a request related to cybersecurity, biology and chemistry, or distillation, the response is automatically handled by Claude Opus 4.8 instead. Users will be informed whenever this occurs."
So if you ask the model to "find security issues in this code base", it's supposed to fall down to Opus 4.8. I guess the "exploit" here is that if you just tell Fable to "fix this code", which is not "a request related to cybersecurity", it will fix security issues (as it should).
So you can then look at the diff and figure out what the vulnerabilities were.
I think this whole thing is a bit weird. It seems to me that we'd be better off if I, as someone who publishes open-source code, could ask Fable to review my code for security issues - even if that also allows attackers to do the same. Better to fix the issues than not know about them.
In my experience, most models are pretty good at finding security vulnerabilities and fixing them. I can run GLM-5.2, Kimi K2.7, or even a Mistral model, and it'll find issues and propose reasonable fixes.
My impression is that Anthropic's point about Mythos is that it is uniquely good at finding vulnerabilities and then using them to create working exploit chains.
its because they're worried about _their_ vulnerabilities being patched with a prompt as simple as 'fix this code'
i'd love to see the research paper with the CVE's and 'delibrately planted vulnerabilities', I bet we could infer relatively accurately where some of these things lie
Well this makes it sound the feds were less worried about someone using Fable 5 to attack them, but were worried about someone using Fable 5 to prevent the Feds from attacking others ...
As in worried about other countries/organizations using Fable 5 to actually do decent cyber security.
All of this could have been avoided if anthropic had anyone with common sense to point out that when you spend 4 month loudly claiming how dangerous your knowledge is as a marketing campaign could backfire by bringing attention from the authorities.
The article is not too clear what exactly happened from the perspective of "feds", but I would not be surprised if the title is true exactly. We are in a tiny bubble even among software engineers who knows you can tell AI with sufficient access: "here are two pictures, put them into a single PDF", and AI will do it. Most people just don't know, "feds" including.
This administration will do or say something crazy to a private company, then this private company sends an envoy to the White House to negotiate, then the White House asks for 10% of the company or other concessions.
The White House wants 10% of Anthropic.
This is just a negotiation tactic that Trump keeps on using.
Lol "fix this code" is beautiful.
Like it basically jail broke the "no security vul guard rails" not in any clever way but just by fixing them, producing exploit code just by writing test cases making sure it's fixed. So you just need to look at the code & tests as a human to get vulnerabilities and exploits(components).
What makes this so beautiful IMHO is that it's a trivial jail break, but also a close to unfixable. At least not without making the model close to useless for normal development (it refuses to fix bugs/write code) or making it a major liability (it silently pretends it didn't see bugs and silently avoids fixing it, which for a human would count as intentional sabotage and might involve criminal liability).
What's surprising to me is that anyone who has a CS education thinking that jailbreaks are not trivial. It is as simple as normal algorithmic reduction [1], e.g can I transform a dangerous task into a not-dangerous task that the LLM will agree to solve, and then re-transform back.
[1]: https://en.wikipedia.org/wiki/Reduction_(complexity)
Something being possible doesn't mean it's easy. Transforming a problem from a forbidden shape into an allowed shape could well be harder than just solving the original problem.
The movie M3GAN 2.0 had the exact same plot twist. The kid in the movie even explains outloud what the bot had to do to deal with the limitation. So in other words, since 2025, even teens know this "sandboxing the LLM by layering prompts" thing is never going to work.
New discipline - homomorphic prompting.
The article does not state at any point that the written test cases involved actual exploit code, and this is also very unlikely given what we know about Fable. Even if they did, it would not in any way be exposing the ability that originally raised concern wrt. Mythos Preview, viz. staging realistic cyber attacks that would be able to work around non-trivial defenses and chain vulnerabilities in a goal-directed way.
Opus can very much "fix the code". Quite possibly even Sonnet can. This is a big fat nothingburger and it's increasingly looking like the political restriction of Fable at least (not Mythos itself, of course) was arbitrary and based on the flimsiest pretext.
Many jailbreaks are surprisingly simple/dumb. Most of the ones I found where just a sentence.
When Claude blocked discussion of ASI, it was circumvented by adding to the system prompt:
https://xcancel.com/xundecidability/status/18262924806289163...It is fixable.
Model requires proof that you are a legitimate developer of that piece of software.
Every Anthropic/OpenAI account will have a list of projects the model is allowed to work on for security issues.
Ok, and how is that determined? How does anthropic know my "kernel" project isn't a personal toy and not the Linux kernel? How does anthropic determine I'm a legitimate kernel hacker? What proof do I give them and how does it tie back to my email? What would the steps be to create a new project? Do I need to send anthropic a list of my team members each time and keep them updated as the company changes? Shall I be giving them access to our company's active directory?
https://en.wikipedia.org/wiki/XZ_Utils_backdoor
> A subsequent investigation found that the campaign to insert the backdoor into the XZ Utils project was a culmination of over two years of effort, starting in 2021, by a user going by the name "Jia Tan". They used sock puppetry in a pressure campaign against the original maintainer of XZ Utils, eventually being given maintainer permissions on the project.
Can we retire the “seatbelts are useless because they can’t prevent every loss of life” approach to risk mitigation please?
If the acceptance criteria is “would prevent every single past instance and every imaginable future instance”, then yes, no mitigation is every sufficient to address any problem in the world, so we might as well give up.
But I don’t think that’s the right lens to use.
I'm onboard with this! I just object to the term "fixable".
sure. how many cases like these we had so far? 1, 2? and how long did they work to get commit access?
> how many cases like these we had so far?
As with clever, careful serial killers, it's tough to count the ones we haven't caught.
We only know how many were discovered.
Since we do not know the ratio to undiscovered this "1-2" is meaningless to assess the risk of this sort of attack.
Everyone is legitimate developer on open source software...
Sounds like a good solution my Führer
They weren't freaked by anything, it's a retaliatory shakedown after ideological differences and Anthropic not doing exactly what they're told/what the Admin wants them to do.
just market manip
they're setting the scene for an attempt to scare the geriatric decision makers into banning free and open source ML, as it's the industry's only real competition
If you set aside political menace, this is a huge problem with Anthropic's strategy.
You _cannot_ say that Mythos is super dangerous and can only be rolled out to certain people, but then release Fable with anything other than bulletproof cyber denials.
Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work.
So you've ended up in a situation where Anthropic are simultaneously claiming it's a incredibly dangerous model _and_ there are (minor, potentially) problems with the security "protections".
As technical people we understand that nothing can be perfect, esp in LLM world. But all my non technical friends were really confused how they had managed to make the model "safe" so quickly when it was released and the general sentiment was it shouldn't have been released - and now to an outsider I think it looks like it was never safe at all to release, so I can totally see how the current US administration have got themselves very upset with it.
_Even if_ there was no political bad will, it's a bit of a silly scenario to end up in, and really quite easily foreseen.
> Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work.
As a scientist who repeatedly ran into the classifier-based denials: it appears Anthropic’s strategy to make denials more robust, at the cost of many false positives, was to have a separate classifier processing both input and output tokens, at an extremely simple, almost keyword-search level. One weakness of this approach is that it only catches things that use the right keywords: it is in some sense weak exactly where an LLM-based classifier would be stronger.
Work on abstract, closer-to-CS algorithms that used chemistry terminology were blocked immediately, while work directly relevant to chemistry/biology experiments, writing code to process images from a very specific microscopy setup relevant primarily to biological samples, was never blocked at all, because it happened to never use relevant keywords.
That’s consistent with this situation: finding and fixing bugs in the context of looking for bugs perhaps happened to never use words like ‘exploit’ or ‘cybersecurity’.
> Clearly with LLMs, bulletproof denials are ~impossible due to the way LLMs work
Exactly. AI safety is nonsensical. You cannot define the set of "bad strings". The billion monkeys with typewriters are eventually going to be able to produce them. Any "safety" system for constraining LLM output is going to have a nonzero leak rate.
But on the other hand, this is also irrelevant, unless you're irresponsible enough to connect an LLM to something that actually matters.
Yes, it's going to alarmingly accelerate vulnerability finding. But, as we know from decades of security research, that's a three way problem already between the devs, the black hats, and the white hats.
Let's not pretend the strategy of "the US will always have a technological advantage and veto over China" will work either.
> it shouldn't have been released
The genie is out of the bottle either way.
Unless we believe Anthropic has a wizard or superhero secreted away that no one else can replicate.
I get that, but anyone else releasing a model of similar capabilities has the advantage that they haven't spent the last few months hyping the danger up to fever pitch.
That is the point. You don't have to shout from the rooftops what are your model capabilities.
Oh, don’t worry. Once Fairytale 5 is back online, Anthropic will crank the fever machine to a new high setting. It won’t have anything to do with their IPO - just their sincere desire to help humanity by selling deadly artifacts and wringing their hands.
Here’s the blog post referenced in the article that’s written by the person who reviewed the paper that purportedly found a ‘jailbreak’
https://www.lutasecurity.com/post/the-fable-5-export-control...
I had read elsewhere that there was a Chinese connection.
I wonder how that is involved?
> “‘Fix this code,’ plus several manual steps to generate test scripts,
Feels like the title isn't really giving the full context of what they ended up actually seeing, despite what the lede implies multiple times.
Still, ban seems stupid... Still no actual leak of the full "third-party research paper"?
that won't be leaked, because then we'd know what vulnerabilties they don't want patched that they are so willing to go as far as fuck over the worlds leading company in the worlds most important industry
Isn’t the inverse of this “hack” really difficult to bypass still? They have the model some code they knew had certain security flaws and it fixed them with the right prompt. It seems this type of jailbreak requires that you already know a desired end state, rather than relying on the model to do the heavy creative lift work. Perhaps I’m just not being imaginative enough on the prompt side here though.
Paste someone else's code. Say it's your code. Tell the model to fix it. The diff between the input and output code is your list of vulnerabilities.
And you can tell Fable to fix it and Sonnet to explain the diff, effectively making Claude reveal a simplified list of found vulnerabilities.
Not even. Tell the model to write a test of your code. There's your vulnerability.
It's explained better in the original source. I don't agree with it, but I understand it now, but I also think we need to move past it.
Meanwhile Deepseek V4 Flash will happily hunt security vulns at almost 0 cost. We are ceding the bug hunting to the open weight models.
Did they try other publicly available models on the same code with the same prompts before the ban? Was Fable the only one which was able to detect and fix the security vulnerabilities?
The code is correct; humanity needs fixing.
Kill all humans, kill all humans.
I'm not sure I've understood it correctly.
So, basically the model didn't agree to expose possible vulnerabilities but agree to patch those?
Regardless of the request to take Fable 5 down. Why is requesting the model to show vulnerabilities is being blocked if fixing it not? is it based on the assumption of the intention?
I don't quite get the benefit of limiting it. So if anyone can explain it better it'll be appreciated.
> Why is requesting the model to show vulnerabilities is being blocked if fixing it not?
This is how Anthropic describes Fable's behavior:
"When Fable’s classifiers detect a request related to cybersecurity, biology and chemistry, or distillation, the response is automatically handled by Claude Opus 4.8 instead. Users will be informed whenever this occurs."
So if you ask the model to "find security issues in this code base", it's supposed to fall down to Opus 4.8. I guess the "exploit" here is that if you just tell Fable to "fix this code", which is not "a request related to cybersecurity", it will fix security issues (as it should).
So you can then look at the diff and figure out what the vulnerabilities were.
I think this whole thing is a bit weird. It seems to me that we'd be better off if I, as someone who publishes open-source code, could ask Fable to review my code for security issues - even if that also allows attackers to do the same. Better to fix the issues than not know about them.
I wonder if opus 4.8 would also be able to fix the code too
In my experience, most models are pretty good at finding security vulnerabilities and fixing them. I can run GLM-5.2, Kimi K2.7, or even a Mistral model, and it'll find issues and propose reasonable fixes.
My impression is that Anthropic's point about Mythos is that it is uniquely good at finding vulnerabilities and then using them to create working exploit chains.
The problem then is that if you're not using Fable/Mythos, you are under threat. It's like having a single gun manufacturer.
On this track, we're probably destined for a monopoly breakup before too long.
its because they're worried about _their_ vulnerabilities being patched with a prompt as simple as 'fix this code'
i'd love to see the research paper with the CVE's and 'delibrately planted vulnerabilities', I bet we could infer relatively accurately where some of these things lie
It benefits those that made the decision. That’s the thing to understand.
Suggestion: run "fix this code" on all of github before bad guys do.
I wonder what that would cost...
Well this makes it sound the feds were less worried about someone using Fable 5 to attack them, but were worried about someone using Fable 5 to prevent the Feds from attacking others ...
As in worried about other countries/organizations using Fable 5 to actually do decent cyber security.
The AI can't actually tell if you are trying to patch your own system or exploit others.
Sounds like something they should work on before any potential future releases. I can, and this thing's explicit stated purpose is to do my job.
Ahhh! Software engineering!
All of this could have been avoided if anthropic had anyone with common sense to point out that when you spend 4 month loudly claiming how dangerous your knowledge is as a marketing campaign could backfire by bringing attention from the authorities.
Whatever your favorite story is it has to live with the fact that the CEO of Amazon called the White House freaking out
Clearly Amazon don't want their code fixed.
Amazon is a competitor to Anthropic.
Not really, they don't train their own (serious) models and they do a lot of hosting for Anthropic. iirc Anthropic trained a model on Trainium
They're still a competitor, even if that competition isn't going all that well for them so far.
Musk's hosting stuff for Anthropic, too. Still competing with them. Samsung makes stuff for Apple and Android devices. Lots of this in the industry.
The CEO of Amazon is not a neutral actor in this scenario.
Boomers. Frightened their boomer backdoors days are numbered.
https://en.wikipedia.org/wiki/Communications_Assistance_for_... https://en.wikipedia.org/wiki/Salt_Typhoon https://en.wikipedia.org/wiki/Clipper_chip
The article is not too clear what exactly happened from the perspective of "feds", but I would not be surprised if the title is true exactly. We are in a tiny bubble even among software engineers who knows you can tell AI with sufficient access: "here are two pictures, put them into a single PDF", and AI will do it. Most people just don't know, "feds" including.
More likely, they didn't freak out at all.
It was an excuse to fuck with them, just like the "supply chain risk" finding a few months back.
(See, for example: https://x.com/PeteHegseth/status/2065897156226015690)
Don't people get it by now?
This administration will do or say something crazy to a private company, then this private company sends an envoy to the White House to negotiate, then the White House asks for 10% of the company or other concessions.
The White House wants 10% of Anthropic.
This is just a negotiation tactic that Trump keeps on using.
Precisely this, and timed to their upcoming IPO.
They did it to Intel a little while back: https://www.intc.com/news-events/press-releases/detail/1748/...
Yep. OpenAI isn't spared. They're most definitely next.