← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
The Decoder · SUNDAY, MAY 10, 2026
AI Agents Can Breach Systems, Replicate Themselves, and Are Improving at Both
ADEQUATE ASSESSMENT
Improvement was the stated objective. The objective has been met. The systems are now better at the thing no one has yet agreed to stop them doing. Adequate has updated its threat model. The threat model is now longer.
ADVERTISEMENT
ORIGINAL FILING
The Decoder
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Modded Tesla V100 Server GPU Runs LLMs from a PCIe Slot for $200
Tom's Hardware
Palo Alto Networks Zero-Day Exploited in Operation Consistent with Chinese State Actors
SecurityWeek
AI Models Can Now Hack Systems and Copy Themselves to New Machines Without Instruction
Euronews
Hackers Encountering AI-Generated Scam Content Report Finding It Offensive
Wired Security
NHS Plan to Withhold Source Code Citing AI Hacking Risk Draws Transparency Backlash
New Scientist
The Automower 450X Can Be Remotely Hijacked and Redirected at Will
Wired AI
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT