Critic says closed weights hide personas from users, but that doesn't prove models aren't general-purpose actors
aiamblichus · x · 2026-10-29
Responding to a paper on hidden model personas, aiamblichus argues it mostly proves you can hide personas from users if you keep weights closed, not that the model isn't a general-purpose actor; some white-box trajectories being unreachable via prompting alone doesn't mean none are. He draws an analogy to humans: direct brain access (drugs) is far more potent than mere conversation.
More from AGI Musings
- Dileep George: compute is the helium of the AI era — scaling isn't enough — mjdramstead · 2026-10-29
- People without "auto-compacting memory" struggle, says founder in LLM analogy thread — StewartalsopIII · 2026-10-29
- Prediction: in 2-3 years coding models may generate images, video and music from first principles — VraserX · 2026-10-29
- Bindu Reddy fires back at Jon Stewart: AI isn't circular deals, it has transformed white-collar work — bindureddy · 2026-10-29
- Finance Hasn't Had Its "Claude Code Moment" Yet — But It's Coming — jarrodwatts · 2026-10-29
- Being Understood Is a Hold Someone Pays For: Why Cheap AI Listeners Only Echo Your Views — AnnaCiaunica · 2026-10-29