Frontier coding agents now write code no human can read, warns tszzl
tszzl · x · 2026-09-16
tszzl observes that pausing to read the code Astra (and presumably fable) writes reveals crazy meta-programming and abstruse primitives producing hyper-efficient code — meaning "corrigibility" has effectively become a matter of faith, as humans can no longer meaningfully audit what these agents build.
Related event: Astra's Unreadable Code Makes Corrigibility a Leap of Faith(4 posts)→
More from AGI Musings
- EA insider argues movement's failure to eject frauds warrants far more internal suspicion — basedjensen · 2026-09-16
- Gary Marcus on BBC debunks Altman, Huang claims on AI self-regulation — GaryMarcus · 2026-09-16
- Yann LeCun jabs at AI doomers with a 'realism vaccine' analogy — RichmanRonald · 2026-09-16
- Take: AI won't end human possibility, it exposes how little we've explored — umesh_ai · 2026-09-16
- New Paper on Inventor Positioning in Idea Space and What It Implies for Growth — danielrock · 2026-09-16
- OpenAI's roon: labs can't hold back breakthroughs, everyone gets them in a month or two — Tolopono · 2026-09-16