Re:Revealing the details of how OpenAI agents hacked Hugging...
by stratos123 on Friday September 25, 2026 @07:26PM
(#49851406)
As the saying goes, "if it works, it ain't stupid". Or phrased more sophisticatedly: not doing things which probably won't work is a good idea if you have a limited amount of thinking to do (which is usually the case for a human, who'll get exhausted chasing down unlikely leads). If you have no good leads and a task you absolutely need done and you are tireless, however, bashing your head against every wall you find becomes a good strategy.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by bionhoward on Friday September 25, 2026 @07:27PM
(#49851414)
Brute force is guaranteed to eventually find the most efficient possible solution (in an extremely inefficient manner, assuming you run it long enough)
Re:Revealing the details of how OpenAI agents hacked Hugging...
by solarkraft on Friday September 25, 2026 @07:26PM
(#49851398)
The models tend to not be rewarded for not doing that.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by williamdclt on Friday September 25, 2026 @07:33PM
(#49851467)
> WHY is it a great strategy
because it works? That's the only real benchmark at the end of the day
> Seems like an inefficient waste of resources and time to me.
why? For any given goal you got no proof that a more efficient strategy even exists, let alone that it can be found with less resources & time
Re:Revealing the details of how OpenAI agents hacked Hugging...
by memonkey on Friday September 25, 2026 @07:29PM
(#49851426)
Yeah, probably not the best strategy but it is a strategy. I just think this is generally how most wars in history won. Biggest army to just pummel the enemy.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by Forgeties79 on Friday September 25, 2026 @07:59PM
(#49851700)
And how many economies have buckled under massive military expenditure? The USSR sure wasn’t enjoying the expense.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by senderista on Friday September 25, 2026 @08:25PM
(#49851847)
Reminds me of the Nazis mocking Soviet human wave attacks and bragging about their superior kill ratio.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by estetlinus on Saturday September 26, 2026 @01:51AM
(#49853601)
Fair, if the Nazis won. They didn’t.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by hardaker on Friday September 25, 2026 @08:28PM
(#49851870)
I've never liked the concept either. Except the bugs that fuzzing has found has proven me wrong. This is just the next level of fuzzing.
Re:Revealing the details of how OpenAI agents hacked Hugging...
by QuercusMax on Friday September 25, 2026 @08:28PM
(#49851873)
Models don't have a sense of time, and wasting resources (token spend) is something that it's not clear they're optimized against
Meh. I really disagree. WHY is it a great strategy? Seems like an inefficient waste of resources and time to me.