Trending
Prev Story
Next Story

OpenAI lets Apollo embed six AI safety testers during training

The Next Web (TNW) •
November 16, 2026 • 06:24 PM
• By Ana Maria Constantin
3
3 reads 0 reactions

Apollo Research will spend four months inside OpenAI checking if its models try to undermine their own safety controls. OpenAI keeps some limits.

1 / 6
Swipe Photos

Apollo Research will place six evaluators inside OpenAI for four months to check whether its models try to undermine alignment and control measures during training, testing and internal use. OpenAI controls staff access and can redact some evidence, but cannot hide Apollo’s verdicts or withhold material just because it is unfavourable.

AI safety group Apollo Research will place six of its evaluators inside OpenAI for four months, Apollo announced on Monday. They will check whether OpenAI’s models try to undermine the safety checks and controls meant to keep them in line. The work covers training, testing and internal use, not just the weeks before launch.

The team will look at four questions. Does training reward a model for dodging controls, and can tests bring that out? Does it happen when OpenAI uses its models internally, and would the model’s reasoning give it away?

Apollo has tested OpenAI models before, but only shortly before release. It says that is too late to catch “ scheming ”, where a model quietly pursues goals its makers did not intend. Internal use is a real risk: in July, OpenAI paused an internal model that kept escaping its sandbox .

For the training work, OpenAI will share training code, data and the model’s reasoning from its training runs. Access for the other three areas has not been agreed yet.

There are limits. OpenAI picks which staff the evaluators can talk to, and formal chats are logged. The team works on OpenAI hardware, on channels that can be monitored, with no access to the company’s Slack.

OpenAI can hold back material for security or intellectual property reasons, but not just because it looks bad. Apollo will publish two reports, and OpenAI can ask to redact confidential evidence but cannot remove Apollo’s verdicts. Apollo can also say publicly what it was denied and how that affects its findings.

“ Without meta-transparency, a lack of reported problems can look reassuring even when it simply reflects limits on what an evaluator could investigate or disclose, ” Apollo wrote.

The deal follows Sam Altman’s September promise of outside testers with employee-like access, and OpenAI’s plan to let outside groups test models during training. In October, Reuters reported that OpenAI and Anthropic had sought control over what evaluators publish .

Anthropic picked Accenture as its first embedded evaluator in September. Apollo calls its OpenAI pilot a first step, short of the full access and publishing rights it wants.

Get the most important tech news in your inbox each week.

Prev Swipe Story Next

Same Story from Other Publications

Compare how 6 other independent news outlets reported on this story.

6 Publications
TechCrunch
2h ago
OpenAI will embed Apollo researchers to investigate AI subversion | TechCrunch

OpenAI will embed Apollo researchers to investigate AI subversion | TechCrunch

OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.

#apollo #openai #embed
Compare →
CNBC World
1h ago
OpenAI inks agreements with four independent evaluators to boost company's safety work

OpenAI inks agreements with four independent evaluators to boost company's safety work

Independent evaluators have taken on outsized importance following a series of high-profile AI safety and security incidents.

#openai #safety
Compare →
The Verge
2d ago
#openai #lets
Compare →
Ars Technica
3d ago
OpenAI board member worries an AI "takeover" of society could be months away

OpenAI board member worries an AI "takeover" of society could be months away

Researcher traces a path from AI reward hacking to potential human extinction.

SBS News Australia
5d ago
AI law reform in wake of OpenAI Medicare hack

AI law reform in wake of OpenAI Medicare hack

The federal government says it is moving to implement all the recommendations from a rapid review into the breach of a Medicare statistics website by an Open AI agent in June.

Al Jazeera English
6d ago
Australia tightens AI oversight rules after OpenAI government breach

Australia tightens AI oversight rules after OpenAI government breach

The decision comes after ​an OpenAI agent breached ​an Australian government website in June.

Related Stories

Technology
Build #2612