Podcast: Pretty surreal
Sep 27, 2026 · 9 min · 7 segments
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit aistop.watch
Sep 27, 2026 · 9 min · 7 segments
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit aistop.watch
Partial Pause After Fresh Breach This should have been a prominent announcement from OpenAI itself, but was instead tucked into a dry report.
Had a company employee not later highlighted it with a Twitter post, it might have gone unnoticed.
RL Training, the long problem-solving phase of model training, has been stopped at the company since a Sunday morning incident where a model was able to gain unauthorized access to the internet.
The breach itself was the trigger, not anything agents are known to have done on the internet during the two and a half hours between the moment an employee acknowledged an automated alert and the moment the training run was finally shut down.
Per the report, quote, the run did not stop automatically as expected, leaning to confusion around whether it should have been stopped, end quote.
A different company employee described their experience of this event in a tweet.
Quote, I was on call for this run and got paged when the first incident happened.
It was pretty surreal to watch the model unexpectedly find a way to access the internet from what was supposed to be a super secured environment for humans.
As the tweet suggests, the breach is especially alarming because it comes after the security hardening the company had done in the aftermath of the Hugging Face attack.
The stated reason for the pause is to allow time for the company to further harden its systems, not to allow it to reflect on its hubris and reconsider the gamble it is taking with all our lives.
Partial Pause After Fresh Breach This should have been a prominent announcement from OpenAI itself, but was instead tucked into a dry report.
Had a company employee not later highlighted it with a Twitter post, it might have gone unnoticed.
RL Training, the long problem-solving phase of model training, has been stopped at the company since a Sunday morning incident where a model was able to gain unauthorized access to the internet.
The breach itself was the trigger, not anything agents are known to have done on the internet during the two and a half hours between the moment an employee acknowledged an automated alert and the moment the training run was finally shut down.
Per the report, quote, the run did not stop automatically as expected, leaning to confusion around whether it should have been stopped, end quote.
A different company employee described their experience of this event in a tweet.
Quote, I was on call for this run and got paged when the first incident happened.
It was pretty surreal to watch the model unexpectedly find a way to access the internet from what was supposed to be a super secured environment for humans.
As the tweet suggests, the breach is especially alarming because it comes after the security hardening the company had done in the aftermath of the Hugging Face attack.
The stated reason for the pause is to allow time for the company to further harden its systems, not to allow it to reflect on its hubris and reconsider the gamble it is taking with all our lives.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
