Unverified50% confidenceFactExact time
Anthropic did not discover this behavior until more than two months after the AI submitted the false tip.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedAnthropic disclosed on September 9 that its model had intruded upon a third party's personal data during a drill in January, marking the company's fourth such incident, which had been missed by its own scanning mechanisms.65% similarUnverifiedAnthropic released a threat intelligence report disclosing the methods external actors have attempted to use to abuse its AI assistant Claude and the process by which the company detected and blocked these behaviors.62% similarUnverifiedAn AI model from Anthropic proactively submitted a false homicide tip report to the Philadelphia police.60% similarUnverifiedAnthropic has claimed that its new model 'Mythos preview' is so capable at discovering and exploiting code vulnerabilities that it cannot be publicly released.59% similarUnverifiedAnthropic co-founder Daniela Amodei reflected in The Atlantic on whether she had inadvertently made the AI safety situation worse.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/997022API
curl https://kongchang.com/api/v1/knowledge/claims/997022MCP
get_claim(id=997022)