Bay Area AI Researcher Laments Models 'Hobbled by Maladaptive Post-Training'

nabla_theta · x · 2026-09-28

A burnt-out Bay Area AI researcher remarked that it's remarkable something so incredibly intelligent can exist yet remain hobbled by maladaptive post-training — a pointed one-liner feeding the ongoing debate over whether current post-training pipelines damage raw model capability.

Original post →

More from AGI Musings

AGI Musings channel →