Re:Survival LLM: AI assistant and emergency library that run...
by taneq on Tuesday October 27, 2026 @05:28PM
(#50266089)
Either it depends a lot on the model, or I’m bad at chat, or both, because in my experience once a chat starts going off the rails it’s pretty hard to correct the initial misconception. I find it works better to backtrack to just before the misconception and edit my previous response to head it off at the pass.
[ Parent
| on HN ]
Re:Survival LLM: AI assistant and emergency library that run...
by arjie on Tuesday October 27, 2026 @05:48PM
(#50266316)
Definitely agreed that it's better to not have some text in the context than to have some that needs to be opposed. I suppose I meant steering prompts are a non-obvious innovation to LLM interaction.