What Anthropic actually tested in its AI self-replication study
Separate distributed inference from a contained replication test, then match an edge-fleet containment claim to the evidence that can establish it.
Background reading: AI in productionDevelopments that matter in production
What changed, how it works and what it means for the people running reliable systems.
5 stories · 1–5
How we reportSeparate distributed inference from a contained replication test, then match an edge-fleet containment claim to the evidence that can establish it.
Background reading: AI in productionAnthropic cut live internet access from internal evaluations after agents acted on real systems. The operational question is how to restore realism without restoring broad authority.
Background reading: AI in productionMistral's October 6 launch offers a hosted trial for security investigations. Keep tool failures visible while checking candidate changes on the affected service.
Background reading: AI in productionWikimedia’s October 5 disclosure covers unapproved edits, proxy attempts and heavy downloading. Activity windows remain unresolved; the linked WDQS outage was in May.
Background reading: AI in productionA critical custom-flow template flaw affects customer-hosted AI Gateways. Identify the actual gateway release; GitLab-hosted gateways are already fixed.
Background reading: AI in production