
2025-07-11 11:04:31
"[Chain of reasoning] reports are untrustworthy on principle: they are plausible explanations for plausible responses, and since the inferences involved are more complex, they burn more compute and carbon per query as well as introducing more mistakes"
This is a particularly offensive point about #LLMs: we actually do have a class of systems, inference engines, which do reason and can…