Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

theregister.com

Post reply on HN
Print view View original

351–360 of 382 posts

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#351

Post by ben_w »

brookst wrote: post #346
pjc50 wrote: post #83

Earlier quoted context omitted.

That depends on whether it's a issue of accidents or a "you have to get lucky every time, we only have to get lucky once" issue.

Death only has to get lucky once. Are you going to stop wearing seatbelts?

I assume pjc50's quotation is referencing a quote attributed to a terrorist group after they failed to assassinate the UK Prime Minister: https://quoteinvestigator.com/2025/12/08/lucky-always/

You're in control of how much danger of accident you expose yourself to.

Nobody is in control of how much danger we are exposed to from other people who are actively trying to do us harm, who will keep going until they get what they're after or are stopped.

For most people, seatbelts are the former. Yeah, not perfect, but they reduce risk. For the latter, if you're known to be a seatbelt wearer, the attacker just does something where seatbelts don't matter.

Every new AI model introduces new capabilities and competencies, so we're not even sure what the true risk levels are yet for self-exposure in this category. The restrictions on AI may be like seatbelts and speed limits, or they may be like "if you install a 1000 HP turbojet engine in your Honda Civic it will no longer be road legal". And this analogy also includes how the first cars had speed limits set low enough to not risk the horse industry, i.e. we may be too cautious.

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#352

Post by thinkindie »

villish wrote: post #343
thinkindie wrote: post #252

As an European, I really don't get where this strategy wants to take the USA to. It's pretty clear everyone is getting scared about changes like this that happen overnight, without clear reason and completely unpredictable. Business requires a stable environment, and Trump is making everything in his power to disrupt business stability. Ultimately, I see the rest of the world (especially Europe) relying less and less…

What European hardware would be used instead?

the same as the American hardware - none.

(although you can say that Europe retained some manufacture capacity)

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#353

Post by scotty79 »

itopaloglu83 wrote: post #339
scotty79 wrote: post #113

Earlier quoted context omitted.

It basically as if you asked it to find ways to enter someone's house and it refused. But then give it exact copy of their house, ask to secure it, which it does and look at what it secured to find out how to get into the original house.

So I was in their house to make blueprints, then I left it, and now trying to get back in? Kidding aside, it practically requires an open sourced project to a certain extent. Regardless, having worked with braindead Opus 4.8 again since this event and missing Fable 5 with every response I received. Feels like Anthropic got a major jump in user base and got knocked out by the friends of the competition.

AI is great at code deobfuscation. AI assisted decompilation should also work great.

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#354

Post by nachopa »

Jensson wrote: post #303
giancarlostoro wrote: post #121

Earlier quoted context omitted.

This is the weird distinction with AI that I've complained about for ages, how can we make it do lawful good, its nearly impossible. Ask an AI to give you regex to filed our racial slurs, and things fall apart really quickly, it scolds you about not saying slurs. Even though regex implies it looks nearly nothing like a slur.

> how can we make it do lawful good Lawful good is impossible if the laws are evil, and here the user dictates the laws so its impossible to make an AI that is lawful good if the user is evil. And users will want a lawful AI that does what the user says, but governments wants AI that does what the government want and not what the user want. I wonder who will win in the end here?

So what happens when your D&D paladin travels to an evil kingdom, or a wilderness area with no laws? Or how does the DM handle a player ignoring the character's code of ethics?

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#355

Post by b--l »

itopaloglu83 wrote: post #336
martythemaniak wrote: post #139

Earlier quoted context omitted.

Yep, people are expanding way too much mental energy on basic bribery. Anthropic will agree to work with the DoD, WH insiders will get some lucrative pre-IPO allocation and Fable will be magically "fixed" and available again.

And until then we’re left with braindead Opus 4.8 where I need tell it 7 times before it does something correctly where Fable 5 just did it in the first prompt. Example: Hey Opus, I’m dealing with this issue on AD and users experience this thing, I tried these. Opus responses with the most braindead call center style respond I’ve ever heard.

The last Opus models were money models--as in designed to make them money.

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#356

Post by b--l »

peter422 wrote: post #277

Also for all the people saying Amazon's part in this couldn't be fabricated, remember that Amazon is a "friend of the administration". During Andy Jassy's tenure, they paid $75MM (wildly outbidding everybody else) for a Melania documentary that grossed ~16MM, a move publicly defended by Jeff Bezos. Any neutral observer could see this was a wild overpay, and after the fact, a terrible business move. But that is not wh…

Ooohh yeah. I forgot completely about that naked shameless bribe.

That one was even more overt than the plane.

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#358

Post by b--l »

ithkuil wrote: post #35
InsideOutSanta wrote: post #23

Earlier quoted context omitted.

> 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 cod…

I wonder if opus 4.8 would also be able to fix the code too

I doubt it. It's a shit a model.

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#359

Post by moi2388 »

I’m not sure I understand. Does this say that you ask Fable to review code with vulnerabilities and implement fixes, then Fable runs the code to verify thereby running the exploits?

If so, that’s expected, isn’t it? Is that not exactly what it’s for?

Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers

#360

Post by SpaceL10n »

functionmouse wrote: post #98
SpaceL10n wrote: post #77

Earlier quoted context omitted.

or are you setting the scene for well-meaning technocrats to back unrestricted AI development in hopes it will bring about utopia while dismissing the damage it could cause in the hands of adversarial groups?

tl;dr super AI is like a necessary bush fire AI isn't that scary. But I've also got some extreme minority opinions like "Never give a website your real name" and "Computers should not be used for banking" and "Don't believe anything you hear online". The worst I see AI/ML doing to society is shining an unmistakable light onto the blind spots people have already been exploiting for decades. Y2k forced us to patch the…

Yes but don't we still try to control brush fires so they don't burn down neighborhoods?
Post reply on HN