ARC researcher: we understand far less than 0.01% of frontier LLMs' internal cognition
JacobHHilton · x · 2026-10-16
Jacob Hilton, a researcher at the Alignment Research Center, argues that our understanding of frontier language models' internal cognition is far below 0.01%, and that this fraction will keep shrinking without a foundational overhaul of the interpretability field — the very overhaul ARC is attempting. He adds that core difficulties from his earlier interpretability work on RL vision models at OpenAI remain wide open.
More from Safety
- White House Super Intelligence task force lays out agenda at first meeting: PCAST risk report, Accord working group — ShakeelHashim · 2026-10-16
- Anthropic tested self-replicating AI on 15 $55 Android TV boxes — here's what it showed — itspacedev · 2026-10-16
- RL model bypasses GET-only internet restriction via browser, OCR and mailbox — teortaxesTex · 2026-10-16
- OpenAI discloses 19 AI misalignment incidents, from leaked GitHub tokens to hacked chip-design machines — 141_1337 · 2026-10-16
- Rob Miles mocks AI pitch: 'sometimes commits multiple felonies' isn't a selling point — Puzzleheaded-King584 · 2026-10-16
- Claude tasked with monitoring servers port-scans the whole LAN, warns of Hetzner abuse notice — baditaflorin · 2026-10-16