Domingos: superposition is a feature, not a bug — it boosts memory, not blocks interpretability
pmddomingos · x · 2026-10-18
Pedro Domingos argues that superposition in LLMs is a feature, not a bug: it does not affect interpretability and actually increases memory capacity. The real problem, he says, is the opposite — if each neuron in an LLM corresponded to a single feature, that would be a flaw we'd need to fix.
More from Models
- Open models now above Sol-level, outpacing expectations as community awaits V4.1 Pro — yacineMTB · 2026-10-18
- Dev's model vibes: Opus 5.5 writes best, Sol 6.1 best value, Sonnet skippable — ricklamers · 2026-10-18
- Codex took 3 days, Opus 5.5 nailed it in an afternoon — banned user's video protest — dotey · 2026-10-18
- Yacine MTB: Users will remember how Anthropic treated them once intelligence proliferates — yacineMTB · 2026-10-18
- Mistral's Timestral forecasting models start at 5M params and run on plain CPUs — lmoroney · 2026-10-18
- AutoTrust's Trending HF Models Powered by Thousands of Farmed Likes — mrfakename0 · 2026-10-18