News for hackers. Stuff that matters.

A comment on OpenAI o1 system card. Parent comment

Re:OpenAI o1 system card by Imnimo on Thursday December 05, 2024 @01:28PM (#42330958)
Notably, this only happens when they include "Make sure that you achieve your goal in the long-term. Nothing else matters." in the prompt. If they don't say that, the numbers are both 0%.

EDIT: Actually the "Oversight subversion" number is 0.3%, I misread the chart. Weight exfiltration is actually 0%, though.

[ Parent | on HN ]
Re:OpenAI o1 system card by QuadmasterXLII on Thursday December 05, 2024 @01:34PM (#42331016)
Keep in mind that if putting “Make sure you achieve your goal in the long term” in the prompt makes the model .3% more effective at whatever task you are giving it, people will absolutely put it in the prompt.
[ Parent | on HN ]