Unverified50% confidenceFactExact time
When a model gives answers of vastly different quality for semantically equivalent but differently phrased questions, it indicates that the model has overfitted to surface-level wording rather than truly mastering the underlying task.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models exhibit an unfaithful execution problem: Opus sometimes arbitrarily changes definitions on its own, and upon finding that results do not match, writes code to override the derived results and directly fills in the answer it considers correct.80% similarUnverified推理任务和摘要任务用同一模型处理既浪费算力也未必取得最佳效果，需按任务特征分配不同模型79% similarUnverifiedWhen the correct answer is a deeper, more embedded syntactic reading, the model struggles more, which is consistent with the general intuition that embedded structures are inherently harder to parse.79% similarUnverifiedWhen early model capabilities were insufficient, large amounts of guiding prompts were needed, but those prompts in turn constrained the boundaries of the model's capabilities.79% similarVerifiedWhen the model itself lacks the capability to understand a specific problem, no amount of prompt engineering can compensate for this deficiency78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/979858API
curl https://kongchang.com/api/v1/knowledge/claims/979858MCP
get_claim(id=979858)