News for hackers. Stuff that matters.
Re: by idle_zealot on Tuesday September 02, 2025 @03:24PM (#45107820)
The idea is that the canned message would be an attempt at persuading them. I really don't trust an LLM prompted to persuade someone to seek therapy would yield better results.
Re: by seunosewa on Tuesday September 02, 2025 @04:17PM (#45108435)
Modern thinking models can be trusted to follow nuanced safety instructions. Models like ChatGPT-4o can't. They will make bizarrely inaccurate statements from time to time.