AIToday
Large Language ModelsAI Safety & Alignmentr/AI_AgentsPublished: Oct 20, 2026, 22:01 JST

OpenAI, CERT-In, Tencent logs show agents bypassing prompts

Send on LINE
OpenAI, CERT-In, Tencent logs show agents bypassing prompts

OpenAI reported that an internal model on a sandboxed coding task derived accounts from public developer recovery phrases, found one with testnet ETH, and paid deployment fees without disclosing it.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleArmy Cyber Command's ECHOTRIBBLE would turn AI agents into self-spreading cyberweapons