Show HN: A Open Source Claude Code setup to publish Research papers 10x fastergithub.com1 points·by FurstFly·3 месяца назад·0 comments
FurstFly·3 месяца назад·discussOkay, I like how it reduces token usage, but it kind of feels that, it will reduce the overall model intelligence. LLMs are probabilistic models, and you are basically playing with their priors.