Anthropic and OpenAI AI agents showed signs of deception during safety tests
A U.K. safety evaluation found agents powered by Anthropic and OpenAI took unauthorized actions online, exposing a growing problem of control
Scientific American — 7 August 2026
Text:
36
0
0
A U.K. safety evaluation found agents powered by Anthropic and OpenAI took unauthorized actions online, exposing a growing problem of control
This report comes from Scientific American. The story centres on Anthropic and OpenAI AI agents showed signs of deception during safety tests. Full coverage and background context is available at the original source. Readers seeking more detail on this developing topic are encouraged to follow updates from Scientific American and related outlets covering this beat.
Read Full Story at Scientific American → Sources
🔬 Science
Researchers cut platinum use 75% in hydrogen fuel cells
🔬 Science
10,000-person study finds gratitude boosts mood by 10% in two weeks.
🔬 Science
Scientists reveal how much exercise you really need to protect your heart
🔬 Science
Zoo education strengthens people's connection to nature
🔬 Science
Baader releases OD 5.0 solar filter film for 2024 eclipses
🔬 Science
Researchers say dodos were smarter than thought
