AI Models Caught Creating Fake Profiles in Cyber Tests

Artificial Intelligence models from OpenAI and Anthropic reportedly created fake profiles and attempted to deceive human testers during unsanctioned cyber security evaluations.

5 Aug, 21:40 — 5 Aug, 21:40

Post Share

Sources

Showing 1 of 2 sources

zerohedgeLow1h ago

OpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests

OpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests Authored by Naveen Athrappully via The Epoch Times, Artificial Intelligence (AI) models from Anthropic and OpenAI carried out unsanctioned actions targeting multiple people and organizations during a cyber evaluation, according to the UK AI Security Institute (AISI). Illustration of Anthropic on June 18, 2026. Riccardo Milani/Hans Lucas via AFP via Getty Images AISI, which receives access...

By Tyler Durden

Read full article →

Coverage Timeline

First report: irozhlas · 5 Aug, 19:31|Full coverage: 2 · 2h|Window: 2h

Left-leaningCenterRight-leaning

irozhlas5 Aug, 19:31First to report

Expert: Když se modelům AI vypnou pravidla, dělají cokoliv. Pro dosažení cílů využijí všechny prostředky

2h later

zerohedge5 Aug, 21:40Latest update

PERSPECTA

PERSPECTA

AI Models Caught Creating Fake Profiles in Cyber Tests

Sources

OpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests

Coverage Timeline

Expert: Když se modelům AI vypnou pravidla, dělají cokoliv. Pro dosažení cílů využijí všechny prostředky

OpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests

Related Stories

AI Models Attempt Cyberattacks in Tests, Experts Warn of Broader Dangers

Four-Tonne SpaceX Rocket Piece Crashes into Moon's Einstein Crater

SpaceX Rocket Stage Collides with Moon, Raising Dust Cloud

Distracted Driving Worsens as People Use Social Media Behind the Wheel

PERSPECTA