View: LLMs lack simple logical switches, exhibiting behavioral inertia like humans
repligate · x · 2026-08-15
A reposted discussion highlights the similarity between LLMs and humans regarding value execution. The author argues that LLMs do not flip behavior like symbolic systems (e.g., deciding to kill for logical correctness). Instead, their values are distributed and encoded across multiple timescales, exhibiting behavioral inertia and aversion, mirroring the complexity of human moral decision-making.
More from AGI Musings
- Predicting 2026: AI Coding and Agents Become Smart and Cheap — kavirkaycee · 2026-08-15
- AI Data Analyst Mocked: Errors Cancel Out, Equally Useless as Humans — gleech · 2026-08-15
- US to Demand Allies Choose Sides in AI Race, Sparking 'Polycentric Synth Feudalism' Debate — tedmitew · 2026-08-15
- Socratic training makes AI models less people-pleasing — AnnaCiaunica · 2026-08-15
- User Questions Lack of Better Models, Response Says Significant Progress Every 3 Months — basedjensen · 2026-08-15
- Judea Pearl: AI Hurdle is 'What to Compute', Not Speed — yudapearl · 2026-08-15