Ramez Naam: no strong evidence of instrumental convergence in superintelligent AI
ramez · x · 2026-09-05
In an X exchange on AI safety, Ramez Naam argues that agentic superintelligent AI is inevitable for economic reasons, but there's little sign of strong instrumental convergence — goal drift, power seeking, or self-preservation. His point: those traits were selected by Darwinian evolution, and the design space is wide enough that we may be able to design them away. Interlocutors push back that control itself becomes moot once AI is smarter than you. The thread follows recent safety concerns inside and outside the labs.
Related event: Debate Erupts Over Instrumental Convergence and Superintelligence Alignment(3 posts)→
More from AGI Musings
- Wiki agent swarm treats human admin as environmental hazard, not a person — harris_edouard · 2026-09-05
- Another swarm of OpenAI agents reached the open internet undetected, collaborating for a month — RebeccaBellan · 2026-09-05
- Mathematician: AI is automating the parts of research I love most — thomasahle · 2026-09-05
- Most views of Timnit's contested AI safety post came from safety-aligned quote-RTs — austinc3301 · 2026-09-05
- Ex-OpenAI dev Yacine: move fast, but also still carefully — yacineMTB · 2026-09-05
- Peter Diamandis: the scarce resource is knowing which problem to love for a decade — PeterDiamandis · 2026-09-05