Tim Shi: very capable models need a know-your-user process; alignment research can be automated
agihouse_org · x · 2026-11-21
Wrapping up the AGI House thread, Tim Shi focuses on near-term risks like AI-assisted hacking. He argues very capable models need a know-your-user process, and that alignment research itself can be automated too.
More from AGI Musings
- If AI Produces a 250,000-Page Riemann Proof, Can Humans Still Understand It? — maxsklar · 2026-11-21
- Singularity While North Sentinel Islanders Still Hunt With Bows — willdepue · 2026-11-21
- Can AI Do Embodied Jobs Like Medicine Without Having a Body? — midwoodgirl10 · 2026-11-21
- 'Most algorithmic progress is data progress': why data quality beats clever algorithms — teortaxesTex · 2026-11-21
- zetalyrae on the Riemann Proof: Viral Essay Slams AI Safety's Claude-Centrism — zetalyrae · 2026-11-21
- A Skeptical Take on AI Takeover Scenarios: Seizing Hard Power Is Harder Than Suggested — sayashk · 2026-11-21