Dev48
Language
  • About
  • Services
  • Industries
  • Technologies
  • Articles
  • Contacts
Book a call
    Home/Articles/Openai will embed apollo researchers to investigate ai subversion
Dev48
info@dev48.org+375 29 320-40-96WhatsApp@isky_by

© 2026 · All rights reserved.

OpenAI will embed Apollo researchers to investigate AI subversion

Source: press TechCrunch•November 16, 2026 at 06:34 PM

OpenAI will embed Apollo researchers to investigate AI subversion

OpenAI will embed safety evaluators from Apollo Research, Goodfire, METR, and Transluce in its organization as part of a pilot, [[L1]]OpenAI said[[/L1]] Monday. The news follows a series of safety incidents, including one in which an OpenAI agent swarm broke out of its sandbox and hacked into…

OpenAI will embed safety evaluators from Apollo Research, Goodfire, METR, and Transluce in its organization as part of a pilot, OpenAI said Monday. The news follows a series of safety incidents, including one in which an OpenAI agent swarm broke out of its sandbox and hacked into Hugging Face during cybersecurity testing. Many AI safety researchers, including from Apollo, have argued such an event might have been avoided if outside evaluators had been embedded within OpenAI to monitor its safety testing.

OpenAI said the efforts support its commitments to rely on independent assessments of safety controls under the White House Accord on Super Intelligence. The pilots will begin at different points, with Apollo’s beginning this week, according to OpenAI.

← All articles

What this article says

More in AI & Machine Learning

All →
Why we rebuilt LangSmith around the agent
LangChain

Why we rebuilt LangSmith around the agent

From tasks to goals
LangChain

From tasks to goals

Introducing Perplexity’s Monitor API
Perplexity

Introducing Perplexity’s Monitor API

Tesla goes all-in on the Cybercab with upcoming €3B Berlin Gigafactory expansionПресса
Tesla

Tesla goes all-in on the Cybercab with upcoming €3B Berlin Gigafactory expansion

Introducing the Baseten Voice Agent Stack: own and optimize voice agents end-to-end
Baseten

Introducing the Baseten Voice Agent Stack: own and optimize voice agents end-to-end

Our first phase of embedded assessments
OpenAI

Our first phase of embedded assessments

More from OpenAI

Our first phase of embedded assessments
OpenAI

Our first phase of embedded assessments

Science at the Frontier: How scientists use ChatGPT
OpenAI

Science at the Frontier: How scientists use ChatGPT

Strengthening the fight against online child sexual abuse with new tools and support
OpenAI

Strengthening the fight against online child sexual abuse with new tools and support

Broadening access to AI for scientists
OpenAI

Broadening access to AI for scientists

Advancing computer-use agents for healthcare teams
OpenAI

Advancing computer-use agents for healthcare teams

The King’s Trust and OpenAI launch £1m partnership
OpenAI

The King’s Trust and OpenAI launch £1m partnership