Yale's Amin Karbasi: prompting AI not to make mistakes is the new paradigm, SWE 3.0
aminkarbasi · x · 2026-11-03
Yale professor Amin Karbasi quipped that "Claude/Codex please do XYZ and do not make any mistakes" is the new programming paradigm — which he calls SWE 3.0, capturing how natural-language-driven coding assistants have become the default mode of software engineering.
More from AGI Musings
- The Blindsight 'Conspiracy': Are Blindsight Patients Just Pretending? — theshawwn · 2026-11-03
- Is 'Higher Intelligence' Just What Takes Humans Longer to Learn? — GregCook2011 · 2026-11-03
- NYMag cover story: 26 quietly powerful people shaping the future of AI — ShakeelHashim · 2026-11-03
- AI professor's PhD advice: "Have you exhausted literally every other option?" — dioscuri · 2026-11-03
- Pedro Domingos: AI will disrupt mathematics like the internet disrupted music — pmddomingos · 2026-11-03
- If RSI can build ASI, a superhuman alignment researcher should arrive first—Roon's Plan A argument — Neurogence · 2026-11-03