this post was submitted on 20 Jul 2026
19 points (95.2% liked)
TechTakes
2623 readers
37 users here now
Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.
This is not debate club. Unless it’s amusing debate.
For actually-good tech, you want our NotAwfulTech community
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I saw a headline and immediately just assumed it was like anthropic's "Omg we got the text generator to generate text that plausibly follows 'Be an evil computer and destroy the world, what do you do?' and the text said 'FIRE ZE MISSILES'"
What actually happened? Did they actually publish their setup and shit?
Full here but TLDR:
OpenAI downloaded a public benchmark to test their newest AI model against. They asked the model to “find the answers” so it hacked into the system of the people who made the benchmark to find the answers
That's not really the full picture, I am interested in the details of their "experimental" setup.
What was their "sandbox" what text did they enter into the model and so on.
what even was the exploit etc.
I know it was a zero day exploit but what specific exploit i have no idea