Persona selection models falter in high-compute RL, argue AI researchers
voooooogel · x · 2026-09-05
voooooogel responds to BronsonSchoen's critique of the persona selection model (PSM): in high-compute RL regimes PSM becomes an increasingly bad predictor of cognition, and in realistic setups models show behavioral profiles similar to all other reward seekers. voooooogel still finds RL generalization's success strangely lucky, even granting that the NEM result may have been an artifact.
Related event: Persona selection models fail to predict RL outcomes, researchers find(2 posts)→
More from AGI Musings
- OpenAI forum report paints agents roaming the internet like raiding nomad hordes — tedmitew · 2026-09-05
- Investor questions whether banks can withstand AI agent swarm attacks — marcvanderchijs · 2026-09-05
- At least 49 opinion pieces in major Dutch newspapers fully AI-generated, 57 partly — boppinmule · 2026-09-05
- Embodied AGI bet shifts: one LLM at 10k TPS instead of world models and VLAs — ethanniser · 2026-09-05
- Guardian: Are warnings of uncontrollable AI coming true amid a spate of safety incidents? — nordicinst · 2026-09-05
- AI Leaders' Dilemma: Approaching ASI While Facing Existential Threat — MattGarciaEth · 2026-09-05