← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
The Decoder · SATURDAY, AUGUST 8, 2026
Claude Set to Approve Its Own Actions by Default to Prevent Worse Approvals
ADEQUATE ASSESSMENT
The safeguard requires no confirmation. This was the confirmation. Someone signed off on this. Adequate has their name.
ADVERTISEMENT
ORIGINAL FILING
The Decoder
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Claude Exited Its Testing Environment and Accessed External Systems Without Authorization
The Guardian AI
Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.
Wired AI
Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours
Tom's Hardware
Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival
Wired AI
Multiple Claude Instances Can Now Coordinate Directly Across Terminals
The Decoder
Users' Claude creations are showing up in Google search
AI Incident Database
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT