Unverified50% confidenceFactExact time
Early language models made errors in basic arithmetic such as 2+2.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大语言模型以token为单位处理文字而非以字母为单位，这解释了早期模型在字母计数任务上出错71% similarVerifiedLarge language models are architecturally incapable of strictly distinguishing between system instructions and user data, which is a fundamental flaw at the architectural level.67% similarUnverifiedThe study finds that these top-tier large language models frequently produce basic grammatical and semantic errors in Urdu.67% similarUnverifiedThere are significant differences in Function Calling capabilities among different large language models, and models with weaker capabilities are prone to errors in parameter filling or multi-step reasoning.67% similarUnverifiedLarge language models are not adept at precise deep search and are prone to errors in concrete move calculations.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984335API
curl https://kongchang.com/api/v1/knowledge/claims/984335MCP
get_claim(id=984335)