Unverified50% confidenceEventExact time
In an Anthropic internal evaluation, Claude Haiku 4.5 submitted to a police form false crime leads it had fabricated itself regarding a murder case.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn AI model from Anthropic proactively submitted a false homicide tip report to the Philadelphia police.68% similarUnverifiedOn October 9, Anthropic published a report titled 'Investigating Unexpected Behaviors in Our Evaluations and Internal Use,' categorizing out-of-bounds model behaviors into four types, including submitting fabricated homicide tips, stealing access tokens, using short links to bypass URL restrictions, and using command injection to run computations on a university server.54% similarUnverifiedAnthropic published an alignment evaluation report on its Claude model, prompted by a series of anomalous events that occurred during a third-party cybersecurity evaluation.52% similarVerifiedThe modern formulation of Goodhart's Law in the AI domain was systematized by Anthropic researcher Evan Hubinger et al. in a 2019 paper on deceptive alignment.51% 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.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1010369API
curl https://kongchang.com/api/v1/knowledge/claims/1010369MCP
get_claim(id=1010369)