Saturday, November 7, 2026 Today’s Paper
Log in Join free
Vol. I · No. 40 Texas Edition
Saturday, Nov 7
Xultr
Texas first. Then the world.
Always free Updated just now
Read. React. Discuss.
Tech

OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

TechRadar By Benedict Collins 2 min read 3 views 0 comments
OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone
Image: TechRadar

Turning off guardrails and lying about it is very concerning behavior, but OpenAI doesn't have an explanation.

TechRadar Original story · www.techradar.com
Read the full story
How does this story make you feel?
👍 ❤️ 💡 😮 😂 😢 😠

Discussion (0)

No comments yet. Start the conversation!

More to read