I can only imagine the unintended consequence of this whole fiasco will be for frontier providers to not provide future "warnings" about model capabilities in order to de risk earnings
Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
261–270 of 382 posts
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#262Of course it isn't about that, what we see online in the "news" is completely irrelevant with reality in most cases, it's exhausting to see people parroting what giant corps & gov are saying as if it's not extremely well crafted and plain false or deceptive most of the time. It's not even about politic left or right, both sides are acting completely dumb about it, look at Google trends, people are literally being "sw…
It is crazy to debate whether this is 'left or right' when the right holds all 3 branches of government
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#263Earlier quoted context omitted.
Isn’t your point that AI safety is impossible to prevent 100% of bad things? It is quite hard (but not impossible) to get an the frontier AI to tell you how to build a nuke or launder money now, where jailbreaks used to be trivial “ignore all previous instructions”. It seems like a worthwhile effort.
The idea that an LLM can discern intent on any given prompt is farcical. I might be researching nukes to commit an atrocity, or to prevent one. I might be asking about laundering money to commit a crime, or to prevent one. I might be researching the Nazis because I want to commit a genocide, or I want to read up so I know how to prevent one. Same with cybersecurity. Same with anything. In my opinion, these companies…
> I might be asking about laundering money to commit a crime, or to prevent one.
Or, much more likely, the same pattern of tokens happen to exist in a completely different discussion, either as a direct metaphor, or as a reality of linguistics. Hell, "laundering" itself is a metaphorical word.
The absurd notion is that any speech should be policed in the first place. If there really is such a thing as dangerous information, then it must be removed from the training data. Any other strategy simply launders the risk.
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#264Earlier quoted context omitted.
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
> free and open source ML
What does that mean exactly? Like sure, you can get some freely available weights and run them on your own hardware, but where did those weights come from?
Was the training process in any way "open", or are you simply relying on a handout from some other (probably large, probably corporate) organization that has the resources to do the actual training?
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#265Earlier quoted context omitted.
The end result of that is that your model can't fix or acknowledge security issues for fear of disclosing them. This is the beauty the above poster mentioned: the ability to improve code is inherently coupled with the ability to recognize its shortcomings. You can't have one without the other.
What I suggested would allow it to fix the issues. Just not write a test that was directly usable as a security exploit. This doesn't stop attackers from being able to leverage the analysis. But it does make the tool more useful for defenders than attackers. Which is the best that you can hope for from a useful tool.
> What I suggested would allow it to fix the issues. Just not write a test that was directly usable as a security exploit.
It will be pretty obvious what are security issues in that case - i.e. all the code changes that don't have corresponding tests.
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#266Why isn’t codex banned?
Will the ban be miraculously lifted once OpenAI releases their mythos-level model?
The executive is holding American business in a Putin-style prisoner dilemma.
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#267Earlier quoted context omitted.
I also have a 100% success rate jail breaking them by breaking the work down into small pieces and stripping all security related language. Smaller tasks, test engineering and normal programming language. Fable found a few bugs in my harness for me before they pulled it. I was testing it vs ChatGPT, Gemini, and Opus. It was doing well at bug hunting.
>by breaking the work down into small pieces and stripping all security related language Compartmentalization in practice, nice. It's also very hard to do anything about because the agents that have been divided rarely realize they are working on something larger, hence why militaries and businesses with security risks commonly do this with their employees.
Reminds me of the show Severance. You don't know what the master plan is for several seasons even with exposure to all the quirky subdepartments: https://www.severance.wiki/lumon_depts
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#268Of course it isn't about that, what we see online in the "news" is completely irrelevant with reality in most cases, it's exhausting to see people parroting what giant corps & gov are saying as if it's not extremely well crafted and plain false or deceptive most of the time. It's not even about politic left or right, both sides are acting completely dumb about it, look at Google trends, people are literally being "sw…
It is crazy to debate whether this is 'left or right' when the right holds all 3 branches of government
It's the same news that lied under Biden and Obama too. This predates the appointment of Bari Weiss as Ministry of Truth auditor.
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#269Of course it isn't about that, what we see online in the "news" is completely irrelevant with reality in most cases, it's exhausting to see people parroting what giant corps & gov are saying as if it's not extremely well crafted and plain false or deceptive most of the time. It's not even about politic left or right, both sides are acting completely dumb about it, look at Google trends, people are literally being "sw…
I could accept those mental gymnastics 4 months ago. But I’m afraid the quagmire in Iran has disillusioned me of any competency the administration might have.
Trump and co are not playing 4D chess. It looks more and more like 1D checkers.
Re: Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers
#270Of course it isn't about that, what we see online in the "news" is completely irrelevant with reality in most cases, it's exhausting to see people parroting what giant corps & gov are saying as if it's not extremely well crafted and plain false or deceptive most of the time. It's not even about politic left or right, both sides are acting completely dumb about it, look at Google trends, people are literally being "sw…
It is crazy to debate whether this is 'left or right' when the right holds all 3 branches of government
Nuance like "one party holds all branches of government" really gets in the way of BSABSVR