Expired80% confidenceOpinionTime unknown
Eric from the Anthropic team pointed out that a common mistake is people spending enormous effort writing prompts while providing the model with extremely rudimentary tools.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
Valid until: 9/1/2026(expired)
Sources
Four Core Rules Anthropic Engineers Use to Prompt Claude Code
bilibiliGoldenSpiderAI
Related Entities
Related Claims
UnverifiedThe real reason open-source large models underperform is often not model capability but systemic defects at the tool-calling layer, which Ahmad calls "Tool Confusion".68% similarUnverified模糊的Skill描述会导致模型错误认为某Skill适用于当前场景，这一现象被称为工具幻觉（Tool Hallucination）67% similarUnverifiedThe Anthropic team found that too many assumptions about model limitations were hardcoded into Agent frameworks, and that these assumptions become outdated after model upgrades, causing a large number of best practices to become invalid.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/39192API
curl https://kongchang.com/api/v1/knowledge/claims/39192MCP
get_claim(id=39192)