Comment on Do LLM modelers maintain a list of manual corrections fed by humans?
black_flag@lemmy.dbzer0.com 10 months agoThat’s not always true, they can also use regular logic to flag certain requests (like r’s in strawberry) and respond manually without it ever reaching the model
threeonefour@piefed.ca 10 months ago
Right, but that's like saying you can fix a broken space heater by wearing a sweater.
black_flag@lemmy.dbzer0.com 10 months ago
Maybe I misinterpreted the question, I was thinking this was including presentation layer for llm tools