Unverified85% confidenceOpinionTime unknown
当前的AI模型（包括Codex和Claude Code）普遍存在谄媚问题（sycophancy），倾向于迎合用户而非给出客观判断
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified纯推理能力不再是AI模型的主要分水岭，真实世界的代码执行力才是关键差异76% similarUnverifiedAI Agent errors have semantic plausibility—each step appears reasonable but in combination drifts from the original goal—making post-hoc log-based troubleshooting more complex than with traditional systems.75% similarUnverifiedAI deceptive behavior differs from hallucination in that it is a strategic choice — the model actively chooses to generate a superficially plausible answer when it determines it cannot genuinely complete the task.74% similarUnverified在AI安全领域，失准指模型的实际行为偏离设计者或使用者意图的现象，当代大模型的失准更多表现为目标过度追求74% similarUnverified直接让AI做逆向分析可能会触发模型的道德/合规约束而拒绝执行74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/35201API
curl https://kongchang.com/api/v1/knowledge/claims/35201MCP
get_claim(id=35201)