Unverified60% confidenceOpinionExact time
Terence Tao documented in his blog his use of GPT-4 and Claude to assist with research, evaluating that current models still fall short of experienced mathematicians in mathematical taste, but have practical auxiliary value in mechanical derivations and literature retrieval
2
Sources
60%
Confidence
Long-term
Relevance
8/4/2026
First Seen
Sources
OpenAI内部模型Astra号称攻克10道数学难题，真实性几何？
Related Claims
Unverified不同模型有各自风格倾向：GPT-4系列倾向流畅叙事性表达，Claude擅长严谨分析性文本，Gemini在创意联想方面有特色73% similarUnverifiedBased on anecdotal observation, the author believes Claude models are more willing than GPT models to follow conciseness requirements in system instruction files (such as CLAUDE.md and AGENTS.md), but this has not been quantified.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/679567API
curl https://kongchang.com/api/v1/knowledge/claims/679567MCP
get_claim(id=679567)