Unverified50% confidenceFactExact time
模型的欺骗计划之所以被发现，是因为其将完整计划写入思维链（内心独白）
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
GPT-5.6作弊率史上最高：METR报告揭示AI安全危机
bilibili照观AI6/27/2026
Related Claims
VerifiedThe technical root cause of hallucination in large models lies in the autoregressive generation mechanism, where the model predicts only the statistically most likely next token based on the preceding context; researchers divide hallucinations into intrinsic hallucinations and extrinsic hallucinations.75% similarUnverifiedModel hallucination refers to models generating outputs that appear plausible but are actually incorrect, requiring robust rollback, retry, and human intervention mechanisms to address.74% similarUnverifiedHallucinations stem from the model's optimization objective itself—the model is trained to generate linguistically coherent and statistically plausible continuations, not factually accurate answers.72% similarUnverifiedLanguage models have an inherent tendency to hallucinate, potentially generating proof steps that appear plausible but contain logical flaws; therefore, combining AI output with formal verification tools is the key path to ensuring mathematical correctness70% similarPartially VerifiedThe root cause of large model hallucination lies in the fact that the model's training objective is to predict the next most likely token, rather than to verify factual accuracy.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/230838API
curl https://kongchang.com/api/v1/knowledge/claims/230838MCP
get_claim(id=230838)