Unverified50% confidenceOpinionExact time
Alehav1 pointed out that a system that only answers questions will never get better at decision-making.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf a system scores primarily on whether an answer is given rather than whether an answer should have been given, then responding 'I don't know' is counted as a failure.57% similarUnverifiedAI is good at answering clearly defined questions, but not at helping to define the questions themselves.56% similarUnverifiedThe paper argues that in legal contexts, declining to answer or signaling uncertainty is often more responsible than forcing a seemingly complete answer, which contrasts with the current tendency of LLMs to always provide an answer.56% similarUnverifiedCompared to providing no reasoning chain at all, faithful reasoning chains brought almost no improvement in answer accuracy.55% similarUnverifiedA request will never carry both the portable reasoning option and native provider control parameters (effort, thinking, thinkingConfig, etc.); when they conflict, the native parameters take precedence.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1126375API
curl https://kongchang.com/api/v1/knowledge/claims/1126375MCP
get_claim(id=1126375)