News for hackers. Stuff that matters.
Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by Retr0id on Tuesday June 16, 2026 @08:00AM (#48553866)
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.
Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by roenxi on Tuesday June 16, 2026 @09:23AM (#48554909)
I think the article just proved that aggressive exploitation is equivalent to normal bugfixing, so it seems like there are some large and important classes of transform that are easy.

It took me a minute of thinking to understand how this could even be considered a jailbreak; if Anthropic are going to turn out models that can't handle "find and develop regression test scripts for bugs in this program" as a prompt then it is going to take serious model crippling. To be able to prompt the model someone will need to already understand secure programming - the model itself won't be able to independently detect security problems without active guidance.

Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by Retr0id on Tuesday June 16, 2026 @09:40AM (#48555171)
> aggressive exploitation is equivalent to normal bugfixing

It isn't, though. The venn diagram has overlap for sure, and the "normal bugfixing" flows may yield results that are useful for offensive security, but a more targeted prompt asking for a specific security objective would be more effective, if allowed.

If the guardrails can be bypassed at, say 50x token cost (due to the agent also pursuing things you don't care about), then it's still pretty effective as a safeguard, because at that cost you might as well hire humans instead.

And, having to "babysit" a model while you re-prompt to work around guardrails strongly limits how much you can scale up your work.

Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by Barbing on Tuesday June 16, 2026 @10:15AM (#48555679)
> If the guardrails can be bypassed at, say 50x token cost […], then it's still pretty effective as a safeguard, because at that cost you might as well hire humans instead.

If humans have to be hired at inflated rates because you’re e.g. the North Korean government, hopefully 50x token costs don’t look competitive.

Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by chillfox on Tuesday June 16, 2026 @10:09AM (#48555594)
Not really, you can just get a smaller unrestricted model to prompt the bigger one
Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by stevefan1999 on Wednesday June 17, 2026 @08:45AM (#48569676)
> If the guardrails can be bypassed at, say 50x token cost (due to the agent also pursuing things you don't care about), then it's still pretty effective as a safeguard

Economic factors doesn't matter to powerful entities such as rival corporations, enterprises, and state power. It only matters to small players who have limited budgets. But I have to also pessimistically assume that Anthropic would go this way, because 1. it does not prevents (you can NEVER prevent) but discourages using it for exploitation, and 2. Anthropic can on the other hand, exploit those small and legit entities by making you pay more, but in exchange effectively enshittifying it. But Anthropic could care two shits about the benefits of us normal, small person. Anthropic have all the motives to do this.

Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by dpoloncsak on Wednesday June 17, 2026 @12:00PM (#48572342)
If you're looking to commit cybercrime I doubt you'd draw the line at token cost. Just find CC dumps on TOR or something
Re:Feds freaked over Fable 5 after simple 'fix this code' pr... by OutOfHere on Tuesday June 16, 2026 @10:41AM (#48556052)
It could be easier when you use a less smart uncensored model to control the smarter but censored one.