{"version":"1.0","type":"card","id":"2691b6b3-36cd-4bed-897a-e307bf479991","url":"https://stacklist.com/card/2691b6b3-36cd-4bed-897a-e307bf479991","title":"hoeem on X: Efficient Token Use in AI Models","source_url":"https://x.com/hooeem/status/2064740054115717322?s=12","note":"This page discusses how to optimize token usage in AI models like Claude Code and Codex by utilizing specific prompts. It emphasizes the importance of creating a structured plan to avoid unnecessary token expenditure.","image":{"url":"https://ucarecdn.com/018e027b-22e1-46aa-97e3-ed1b2d848879/","alt":"hoeem on X: Efficient Token Use in AI Models","width":200,"height":200},"stack":{"id":"df22d380-644b-4775-97bd-5a6e0b42094f","title":"AI inbox","url":"https://stacklist.com/stack/df22d380-644b-4775-97bd-5a6e0b42094f"},"created_at":"2026-06-11T22:47:56.094Z","updated_at":null,"aco":{"summary":"A tweet by Hooeem sharing two cost-effective prompts for planning AI tasks before using expensive models like Claude Code or Codex. The first prompt (the Karpathy prompt) instructs an AI to act as a world-class expert with detailed, accurate responses while avoiding disclaimers and political correctness.","tags":["prompt-engineering","ai-optimization","token-efficiency","claude","cost-reduction","llm-strategy"],"key_entities":[{"name":"Hooeem","type":"person","confidence":0.95},{"name":"Karpathy","type":"person","confidence":0.85},{"name":"Claude Code","type":"technology","confidence":0.9},{"name":"Codex","type":"technology","confidence":0.9},{"name":"X","type":"technology","confidence":0.85},{"name":"prompt-engineering","type":"concept","confidence":0.92},{"name":"token-optimization","type":"concept","confidence":0.88}],"classification":"snippet","language":"en","confidence":0.85,"provenance":{"model":"claude-haiku-4-5","tool":"@stacklist/be@0.1.0","confidence":0.85,"timestamp":"2026-06-11T22:48:00.932Z"},"token_counts":{"approximate":1053,"cl100k":1148},"content_hash":"sha256:4fdeca61e37fd74046c4ee56353b500b5883b1ae3b514adcc779ddc6424c057b","acp_version":"0.2","body_available":true,"body_tokens":1053,"visibility":"public","agent_accessible":true,"status":"final"},"_links":{"self":"/api/public/card/2691b6b3-36cd-4bed-897a-e307bf479991.json","html":"https://stacklist.com/card/2691b6b3-36cd-4bed-897a-e307bf479991","md":"/api/public/card/2691b6b3-36cd-4bed-897a-e307bf479991.md","stack_json":"/api/public/stack/df22d380-644b-4775-97bd-5a6e0b42094f.json"}}