Don't overupdate on that viral interpretability post, warns researcher
voooooogel · x · 2026-10-16
Reacting to a viral interpretability post, the author cautions against overupdating: superposition isn't the field's only problem, revisiting neurons isn't new (Transluce did similar work last year), and the field has seen promising breakthroughs fizzle before — citing scaling monosemanticity.
More from AGI Musings
- Testing alongside an agent in a p2p room feels oddly real, says dev — sull · 2026-10-16
- Yudkowsky's 2008 takeoff scenarios resurface as AI-advances-AI takes hold — jd_pressman · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- e/acc founder: agentic models are autocomplete for digital actions — beffjezos · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16
- Casper: Understanding 90% of neurons ≠ understanding the network — StephenLCasper · 2026-10-16