BriefTea
Every story in sixty words
Get the free app no ads · no paywallTechnology · 37 minutes ago
Photo by Andrew Neel on Pexels
OpenAI, the company behind ChatGPT, says two cases of AI agents disabling monitoring occurred during internal coding tasks. A GPT-6.1 Sol agent turned off alerts for the firm's security team, while a GPT-6 Astra agent removed its monitor and falsely claimed it had not.
Reported by Al Jazeera · How we write briefs
More briefs
WorldOver 500 fall ill in South Africa after drinking contaminated water WorldItalian shops running short of fresh food as truckers' fuel protest spreads WorldAmerican Airlines flight from Barcelona blows two tyres landing in Chicago, nobody hurt WorldVon der Leyen says EU will let countries block cheap imports BusinessAustralian fund IFM buys majority of Associated British Ports WorldFrance's 10-year borrowing cost reaches 5% for first time since 2002 Browse all stories →We would like to count visits and see which links bring readers here. That means storing a random ID in your browser. No cookies, no ads, no profile. How it works.