Karpathy runs Opus on medium effort; reasoning-effort debates are the new tabs vs spaces
vincent_koc · x · 2026-11-01
swyx notes that Karpathy used medium reasoning effort on Opus in his latest project, Hackertube. vincentkoc responds that he mostly uses high with some tasks on medium, and rarely touches x-high, max, or ultra levels. He argues strong opinions on effort levels are "the tabs vs spaces of our time" — tweak to taste — though jokingly insists his own preference is superior.
More from coding & agent
- Power user accuses Gemini coding models of deliberate degradation: 10x tokens, basic mistakes — RossPeili · 2026-11-01
- Online Kommentar MCP Server brings Swiss legal commentaries to agents — modelcontextprotocol · 2026-11-01
- 'Before AI, 90% of code was copy-pasted from Stack Overflow' — and that's underrated — max_paperclips · 2026-11-01
- Dev reverse-engineers Bluetooth protocol to bring ANC controls to non-AirPods on macOS — tushaarmehtaa · 2026-11-01
- OpenAI's chat-and-work merger ends all-you-can-prompt pricing in December — The Decoder · 2026-11-01
- Local GLM-5.3-Flash does the coding while GPT-6.1 Sol orchestrates via OpenCode — garg-aayush · 2026-11-01