tszzl: automated research can crack mechanistic alignment — 'it's more like math than cell bio'
tszzl · x · 2026-11-15
Prominent investor-commentator tszzl says he's more bullish than most on solving mechanistic alignment via automated research, enabling strong guarantees on model behavior. "All the component parts are on the computer — it's more like math than cell biology," he argues, offering a big-picture take without technical detail.
More from AGI Musings
- OpenAI reportedly pivots safety strategy within 8 weeks; critic says alignment evals are broken — marcvanderchijs · 2026-11-15
- Starship catch proves reusability, paving way for orbital data centers — Dr_Singularity · 2026-11-15
- Ratsphere nostalgia: the 2014 "kill God" transhumanist line and Anthropic's torch — teortaxesTex · 2026-11-15
- AI future thought experiment: poor free researchers vs wealthy thought-controlled masses — jessi_cata · 2026-11-15
- California professor teaches 30 classes across 9 colleges for $800K/year using pre-recorded lectures — alvelda · 2026-11-15
- Aaron Levie: work will become coding-shaped to fit what AI agents are good at — RaphaelDabadie · 2026-11-15