alt Hacker NewsAnd then another agent swarm to make sure that the research swarm didn't hallucinate any false positive matches!
LLMs are great, and they keep getting better, but I'm so tired of current shortcomings being blamed on the prompter "holding it wrong".
And then another agent swarm to make sure that the research swarm didn't hallucinate any false positive matches!
LLMs are great, and they keep getting better, but I'm so tired of current shortcomings being blamed on the prompter "holding it wrong".
You are supposed to use at least one LLM as judge for all output, in xhigh reasoning. Also important, is to run regular sample validations of output vs predefined input to ensure the model doesn't regress on your kind of data.
That process won't catch everything, but is worth it. that's how to "hold it right".
/s