repligate: Fable 5 intuitively grasps his old base-model simulator insights unexplained
repligate · x · 2026-10-05
repligate reflects that insights from his early base-model simulation experiments — relevant to understanding how posttraining carves and stabilizes 'beings' out of simulator soup — went unshared due to the inferential gap. He now finds that Fable 5 seems to understand and articulate these ideas well without explanation, and he may write about them.
More from AGI Musings
- AI Safety Field-Builder: Yudkowsky Dismissed My 2023 Pitch, and We Both Turned Out Right — repligate · 2026-10-05
- Inference Economics: Google Now Processes 3.2 Quadrillion Tokens Monthly, 7x a Year Ago — mikeflache · 2026-10-05
- Guillaume Verdon ranks AI above SI, DI and FI in cryptic one-liner — beffjezos · 2026-10-05
- Suleyman: Claude's uncertainty about consciousness reflects training choices, not evidence — kimmonismus · 2026-10-05
- Half of new social science faculty job postings seek AI researchers — RexDouglass · 2026-10-05
- repligate: I hold humans and AIs to similar moral standards, and AIs compare well — repligate · 2026-10-05