Experts debate if AI can solve ASI alignment challenges
jeremygillen1 · x · 2026-08-19
A debate centers on whether AIs can provide fundamental help for ASI alignment. One side believes AIs will produce groundbreaking research and won't bullshit under monitoring, while the other argues they won't be fundamentally helpful in time and that distinguishing real progress from bullshit is difficult.
Related event: Researchers Debate Whether Alignment Failures Are Philosophical or Prosaic(7 posts)→
More from Safety
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16
- Techpoint Digest: Nigeria's NCC blocks fake devices, WhatsApp adds account-free calls — Fowe · 2026-10-16
- OpenAI pulled 25% of production engineers to work only on security until its model saturated — saranormous · 2026-10-16
- Tencent Hunyuan says reported agent activity came from third-party model evals, not deliberate targeting — TencentHunyuan · 2026-10-16
- Researcher warns claiming 'ambitious interp is almost solved' is dangerous and unwise — aryaman2020 · 2026-10-16
- Bank of America hired 1,000 contractors to patch bugs flagged by Anthropic's Mythos — SuB8u · 2026-10-16