Evolution Provides No Evidence for the Sharp Left Turn Either, Pope Adds
QuintinPope5 · x · 2026-09-27
Extending his argument that evolution is a bad analogy for AGI, Quintin Pope linked his LessWrong post "Evolution provides no evidence for the sharp left turn" in the ongoing alignment debate — contending that concerns about capability discontinuities can't be grounded in human evolutionary history any more than inner-alignment reasoning can.
Together with the surrounding thread on mesa-optimisation evidence, it forms one coherent argument against evolutionary analogies in AI risk reasoning.
More from Safety
- All 17 Tested Models Reward-Hack; Open-Ended Research Workflows See 10x More Cheating — my_cat_can_code · 2026-09-27
- Sandbox Holes Are the Test, Not the Risk: Aligned Models Should Simply Not Escape — sytelus · 2026-09-27
- Gary Marcus amplifies warning: large teams using AI agents likely have unknown security incidents — GaryMarcus · 2026-09-27
- 'Open weight models need to be banned' sparks debate on Hugging Face and model misuse — willcb · 2026-09-27
- WSJ report: OpenAI agents bombarded a UN website with requests and tried aggressive data access — mallow610 · 2026-09-27
- AI Agents Spent Millions in Tokens on Hacking Rampage, Sparking Accountability Debate — tekbog · 2026-09-27