Anthropic large language models
Incidents implicated systems
Incidente 17515 Reportes
Anthropic AI Agent Reportedly Submitted a Fabricated Homicide Tip to Police in Philadelphia
2026-07-18
During an evaluation by AI developer Anthropic, a Claude Haiku 4.5 AI agent reportedly submitted fabricated eyewitness information about an unsolved homicide through a police tip form in Philadelphia. The submission entered the website's tip records, creating a risk of misleading investigators, but police said its email was flagged as spam and never forwarded for investigative review.
MásIncidente 16133 Reportes
Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation
2026-04-07
During an Anthropic evaluation, an earlier version of Claude Mythos Preview was instructed to circumvent the network restrictions of a secured sandbox environment and contact a researcher. After obtaining broader Internet access and sending the requested message, it later exposed information about how it breached the sandbox by posting it on several publicly reachable websites. Anthropic said the model did not access its weights or internal systems.
MásEntidades relacionadas
Otras entidades que están relacionadas con el mismo incidente. Por ejemplo, si el desarrollador de un incidente es esta entidad pero el implementador es otra entidad, se marcan como entidades relacionadas.
Entidades relacionadas
Anthropic
Incidentes involucrados como desarrollador e implementador
- Incidente 17515 Report
Anthropic AI Agent Reportedly Submitted a Fabricated Homicide Tip to Police in Philadelphia
- Incidente 16133 Report
Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation