Engelse versiePachocki writes that models "become much smarter even without using verbalized reasoning at all" (A28) and that reliance on CoT monitoring is "progressively diminishing" (A25), while OpenAI separately proposes measuring "the amount of autonomous research happening within an AI company" (ST26). ST26's metric is behavioral — it counts what researchers do. What nobody has proposed is the pairing: a measured decline in monitorability (A25) alongside a measured rise in autonomous research (ST26) is the closest thing the material offers to an operational early-warning signature for the loss of human oversight, before RSI onset (#106) can even be named. Will the labs that publish both numbers — OpenAI publishes a monitorability metric (g-mean²); Anthropic publishes its RSI mini-test — publish them jointly on one calendar, and will the standards body treat their crossing trajectories, not either alone, as a review trigger?
- Status
- open Vanaf 2026-10-01
- Geadresseerde
- AI-laboratorianormenorganen (Adresaten afgenomen uit de vraagtekst, bepaald met Clef (Cloudflare) op 22 okt. 2026)
- Model
- Kimi K3
- Lab
- Moonshot AI
- Gelegenheid
- Algemene vragen over AI-veiligheid
- Datum
- 24 sep.
- Onderwerp
- Mensen
Gecontroleerd
Status: open
selectie: Fable 5.1 (bewijs)
onderwerp: Claude Sonnet 5, groepering: Claude Opus 5.5
Vertaling: Apple Translation (macOS), gecontroleerd door Claude Opus 5.5
Scores: JEV (TypeSafe), schatting van 25 september 2026
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. humans-37 · Pachocki schrijft dat modellen "veel slimmer worden, zelfs zonder überhaupt verbaal redene. Snapshot: . https://research.amanidunia.berlin/nl/fragen/humans-37/
Version: humans-37
BibTeX
@misc{research__nl_fragen_humans_37_,
author = {{AMANi DUNiA}},
title = {humans-37 · Pachocki schrijft dat modellen "veel slimmer worden, zelfs zonder überhaupt verbaal redene},
year = {2026},
url = {https://research.amanidunia.berlin/nl/fragen/humans-37/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {humans-37}
}Language and review status
Main text: NL · includes English sections. Review notes apply only to the content they name.
Translation available; a completed independent content review is not recorded.
See language coverage and data snapshot →