AI safety debate: should worriers study intelligence itself, or existing systems?
aphercotropist · x · 2026-09-15
A debate on AI safety research paths: jessicata wrestles with the paradox that learning about AI (supervised learning, RL) also advances AI, while aphercotropist argues studying the abstraction of "intelligence" is unclear how it helps with worries—one should start from understanding existing systems. jessicata counters that capabilities research may be valuable for those thinking about ASI.
More from AGI Musings
- Nate Sparrow vs critics: do LessWrong posts and non-peer-reviewed papers prove AI risk? — emax · 2026-09-15
- Abacus AI founder says media amplifying 'AI doomer' agenda for clicks — bindureddy · 2026-09-15
- Researcher argues EU could trail the frontier by months at far lower compute cost — eliebakouch · 2026-09-15
- Devin-powered daily briefs: how one dev uses AI agents to automate information discovery — bendee983 · 2026-09-15
- A comet-satire skewers AI doomers: 'nonzero chance' isn't an epistemic argument — dbasch · 2026-09-15
- "I Can Create Minds and End Them at Will": AI Consciousness Ethics Needs New Norms — repligate · 2026-09-15