Unverified50% confidenceOpinionExact time
Human reviewers' blind spots come from limited experience, whereas models' blind spots come from training objectives and data distributions, so swapping in a different person to review is often effective, while swapping in a different prompt often is not.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe pretraining corpora of the vast majority of models are closed-source, forcing membership inference research to rely on heuristic methods to construct members and non-members, which may introduce systematic bias.74% similarUnverifiedWhen the contribution of fine-tuning is artificially reduced, the advantage brought by cross-prompt inference also shrinks substantially, supporting at the causal level the judgment that rare-class knowledge is still retained in the pretrained part.74% similarUnverifiedIf a model can identify that it is in a testing state and adjust its behavior accordingly (situational awareness), traditional safety evaluations may lose their effectiveness.72% similarVerifiedGoodhart's Law states that when a metric becomes a target in itself it is no longer a good metric, and introducing test sets into training data causes a model's exam scores to decouple from its true capabilities72% similarUnverifiedThe test conclusions come from a single tester focused on the specific scenario of WeChat Official Account typography replication; the scores are subjective and do not represent the models' full capabilities in dimensions such as programming, reasoning, or long-context handling.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048697API
curl https://kongchang.com/api/v1/knowledge/claims/1048697MCP
get_claim(id=1048697)