rgblong: real risk lies in instilling contradictory views of consciousness and goals in models
rgblong · x · 2026-09-18
Continuing the debate, rgblong clarifies his specific safety concern: embedding contradictory or incoherent views about consciousness, goals, and self into models. It's an addendum to the discussion of Microsoft's stance on model self-presentation.
Related event: Microsoft AI CEO Suleyman Warns Anthropic May Be Training a Moral Agent(16 posts)→
More from AGI Musings
- Databases to distributed systems: every systems skill is merging into AI inference and hardware — Abhishekcur · 2026-11-02
- Limitless analogy: smarter people may gain far more from superintelligence — McDonaghMatthew · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- Avoiding AI brain rot: Miles Cranmer's lecture on learning with AI — _ScottCondron · 2026-11-02
- Yacine mocks "autonomous research" hype as Naam argues RSI loop needs 5-10x boost to run away — yacineMTB · 2026-11-02
- Vitalik's "post-AI cryptography": pseudonyms are dead, per-action anonymity is in — devanshmehta · 2026-11-02