gpt-6POST
OpenAI has nerfed GPT-6 Sol's offensive security research ability, tester says
A poster says testing on the day showed GPT-6 Sol starting to refuse offensive security research requests, including authorized security research.
Jenish Sojitra
@_jensecArchived 2026.09.28Originally posted 2026.09.28
Jenish Sojitra @_jensecOriginally posted 2026.09.28
In my today's testing it looks like @OpenAI Nerfed the GPT 6 SOL to make it refuse offensive security research request. Including any authorised security research
x.com/_jensec/status/2104320745400897827Archived 2026.09.28 09:56