Discussion on Post-Training: Persona concept undersold, RL reshapes dispositions

voooooogel · x · 2026-08-31

The discussion suggests that the Persona (PSM) concept is vague and undersells what post-training can achieve. A better perspective views models as bundles of dispositions, tics, and preferences from the token to context level, with RL acting to push, pull, and stretch this bundle.

Related event: Researchers Debate Whether "Persona" Is a Useful Abstraction and What RL Training Actually Changes(6 posts)→

Original post →

More from Models

• OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
• Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
• NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
• RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
• Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
• Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16

Models channel →