livgorton pushes back on Cammarata: critique vs. calling prior work all wrong
livgorton · x · 2026-10-16
Researcher livgorton responds to Cammarata's 'Neural Networks Are Already Clean': preferring mechanisms over features is fine, but claiming one approach is too hard and easier ones suffice is very different from saying all prior work rests on errors. She also questions whether he denies superposition as defined in the literature, and plans a fuller writeup.
More from Research
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16
- Survey: AI agent evaluation is getting realistic but still fails to measure safety and reliability — burkov · 2026-10-16
- COVA-SFT dataset trains models to solve text problems with visual chain-of-thought — yoavartzi · 2026-10-16
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- Tsinghua's CoTranslator distills reverse CoT to boost 4B model math scores — Tsinghua · 2026-10-16