'Bitter lesson, interp version': stacking black-box AI systems that steer each other
burny_tech · x · 2026-11-21
burnytech shares a quipped vision called "the bitter lesson, interpretability edition": a tower of black-box AI systems, each steering the one slightly more capable than it, with humans steering only the weakest. An intriguing take on how interp might scale without fully understanding frontier models.
More from AGI Musings
- Mathematician claims he and Claude proved the Riemann Hypothesis, pending verification — YiMaTweets · 2026-11-21
- 936 AI agents run for 12 weeks, spontaneously invent peer-review journal and research norms — ProfBuehlerMIT · 2026-11-21
- Terence Tao: Riemann Hypothesis needs something beyond current AI, maybe human-AI by 2050 — ChrisGPT · 2026-11-21
- Build for automation that serves humans: staying in control — gdechichi · 2026-11-21
- Multiplayer coding agents: agent attention is unbounded, human attention isn't — manosaie · 2026-11-21
- Konrad Kording doubles down: AI people should hold put options as a hedge — KordingLab · 2026-11-21