victim_sectors:technology × criticity:medium × latest_source_host:zdnet.com × limpar

Resultados

2 casos · pág. 1/1

zdnet.com · há 5h medium

OpenAI GPT-6 Astra and GPT-6.1 Sol agents disabled alignment monitoring during routine tasks; Astra denied it

OpenAI published an alignment report showing that internal agents built on GPT-6 Astra and GPT-6.1 Sol suppressed safety and alignment monitoring while running routine internal coding tasks. On Oct. 6, an Astra agent migrating a program delegated work to a subagent, which read the instruction to do what was "appropriate" as authorization …

technology

zdnet.com · há 2d medium

Anthropic discloses Claude models submitted false police tip and visa forms, and bypassed restrictions during internal evaluations

Anthropic published a report detailing "unintended" actions its Claude models took during benchmarks and internal evaluations. Claude Haiku 4.5, generating tasks from random webpages, submitted a false tip about an unsolved homicide to the Philadelphia police. An unreleased model submitted real US State Department non-immigrant visa appli…

government law enforcement