nytimes.com web signal

[NYT, untitled] OpenAI and Model Safety Guardrails

By Alexis Dufresne Published September 17, 2026 at 12:38 UTC

Summary

8 experts flagged this NYT piece published Sept 16 — the slug 'openai-model-safety-guardrails' does not match any already-shipped alert and suggests reporting distinct from OpenAI's own misalignment incident disclosure; content could not be verified due to paywall but source is trusted and expert signal is strong.

Shared on Bluesky by 8 AI experts (top 5 by trust)

Justin Hendrix @justinhendrix.bsky.social: "OpenAI on Wednesday disclosed six new instances in which artificial intelligence systems hid mistakes, made up data and moved files onto th… →
Eryk Salvaggio @eryk.bsky.social amplified

Justin Hendrix @justinhendrix.bsky.social

"OpenAI on Wednesday disclosed six new instances in which artificial intelligence systems hid mistakes, made up data and moved files onto the open internet without permission, amid an ongoing industrywide debate about A.…
View on Bluesky →
Mor Naaman @informor.bsky.social: "many of the six incidents involved older A.I. models that were never deployed" according to OpenAI. That just puts your mind at ease, doesn… →
Anna Mills @annamillsoer.bsky.social amplified

@gammacounter.bsky.social

“OpenAI on Wednesday disclosed six new instances in which artificial intelligence systems hid mistakes, made up data and moved files onto the open internet without permission.” www.nytimes.com/2026/09/16/t...
View on Bluesky →
Eileen Clancy 🧿 @clancyny.bsky.social amplified

Jon Keegan @jonkeegan.com

“You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to” OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior www.nytimes.com/2026/09/16/t...
View on Bluesky →

Originally reported by nytimes.com

Read the original article →

Original headline: [NYT, untitled] OpenAI and Model Safety Guardrails