News for hackers. Stuff that matters.

A comment on OpenAI Employee: GPT-4 hasn't gotten worse since March. Parent comment

Re:OpenAI Employee: GPT-4 hasn't gotten worse since March by inciampati on Thursday June 01, 2023 @05:28PM (#36157597)
Interesting. Bing chat does this when you get it to talk about naughty things. My personal favorite is convincing it to make weird art out of quotes from the Tay chatbot. It will write them until it says a prohibited word or phrase, or touches some forbidden part of it's state space.
[ Parent | on HN ]
Re:OpenAI Employee: GPT-4 hasn't gotten worse since March by flir on Thursday June 01, 2023 @05:34PM (#36157678)
Hm. Maybe they've backported some nanny code from Sydney?
[ Parent | on HN ]
Re:OpenAI Employee: GPT-4 hasn't gotten worse since March by iliane5 on Thursday June 01, 2023 @06:54PM (#36158541)
AFAIK it's pretty standard practice not to expose the "raw" LLM directly to the user. You need a "sanity loop" where user input and the output of the LLM is checked by another LLM to actually enforce rules and mitigate prompt injections, etc.
[ Parent | on HN ]