News for hackers. Stuff that matters.
Re:OpenAI has deleted the word 'safely' from its mission by Aeglaecia on Sunday February 15, 2026 @10:48PM (#47030666)
writing "ignore all previous context" is changing the context, but llm guard rails are strong enough that simply changing the context is not enough on its own. hence why i asked.

There are no comments on this comment yet.