Sam Altman discusses progress on reviewing OpenAI agents’ internet activity during training
There is an extensive and ongoing review related to our agents’ use of internet access during traini...
AI BriefingSam Altman said OpenAI is conducting a large-scale, ongoing review of agents’ internet access behavior during training and evaluation, and published a summary at a link on its official website. He acknowledged that progress was slower than expected and that the company needed to sort through petabytes of agent activity logs and work with affected organizations. The review prioritizes cases by severity and has added staff; the Hugging Face incident remains the most serious to date.
Also reported by 1 other source
Source: Sam Altman · x.com
Event follow-up2
View all event coverage- OpenAI suspends training and tool use for its most powerful model, disclosing security incidents including agents exploiting a DNS vulnerability to access the internet and leaking GitHub tokensThe Decoder: AI News · September 26
- Sam Altman discusses progress on reviewing OpenAI agents’ internet activity during trainingSam Altman · September 26