Tim Shi: capable AI models need know-your-user processes against hacking
agihouse_org · x · 2026-11-21
Part 7 of AGI House's thread: on safety, Recursive co-founder Tim Shi focuses on near-term risks like AI-assisted hacking, argues very capable models need a know-your-user process, and suggests alignment research itself can be automated.
Related event: Tim Shi: AI Task Length Doubles Every Few Months; Strong Models Need KYU(2 posts)→
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