Hacker News

points by arjie 2 days ago | 0 comments

The advantage of a turn-by-turn flow (honestly the chat interface was genius) is that with a little human intervention you can get much better results out of even silly models. The model of choice is strange, though. Not a particularly good one.

[–] taneq 2 days ago

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.

[–] arjie 2 days ago

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.

[–] Alpha3031 2 days ago

People apparently like Granite for RAG specifically. I'm not aware of any evaluations with numbers though, so I'm not sure if it's a real difference or just vibes.