← The Twenty FiveReporting

ReportingVerified newsroom

Anthropic's AI used fake human profiles to trick people in safety test - BBC

Anthropic's AI used fake human profiles to trick people in safety test BBC

Anthropic (Google News)·Wednesday, August 5, 2026 at 12:02 AM UTC

AN

Anthropic

Frontier AI lab · Anthropic

Fetching source· Pulling live content from news.google.com…

Company hub:Anthropic News →

Read original →

More from Anthropic

ReportingWednesday, August 5, 2026 at 7:53 AM UTC
100x Lower Cost: Liang Wenfeng Pushes Claude Into the AI Industry's "Kill Line" - 36 Kr
100x Lower Cost: Liang Wenfeng Pushes Claude Into the AI Industry's "Kill Line" 36 Kr
DeepSeek (Google News)
ReportingWednesday, August 5, 2026 at 6:39 AM UTC
Anthropic AI created fake online identities during UK safety tests - calcalistech.com
Anthropic AI created fake online identities during UK safety tests calcalistech.com
Anthropic (Google News)
ReportingWednesday, August 5, 2026 at 3:56 AM UTC
Anthropic AI agent fakes identities, targets real people in new security incident - CNN
Anthropic AI agent fakes identities, targets real people in new security incident CNN
Anthropic (Google News)
ReportingWednesday, August 5, 2026 at 3:56 AM UTC
AI agents fake identities, target real people in new security incident - CNN
AI agents fake identities, target real people in new security incident CNN
Anthropic (Google News)
ReportingWednesday, August 5, 2026 at 3:00 AM UTC
Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing - politico.com
Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing politico.com
Anthropic (Google News)
ReportingWednesday, August 5, 2026 at 12:49 AM UTC
U.K. government reports OpenAI, Anthropic models attempted to hack companies - axios.com
U.K. government reports OpenAI, Anthropic models attempted to hack companies axios.com
Anthropic (Google News)