Tag: cyber-evals
All the articles with the tag "cyber-evals".
-
GLM-5.3's Exploit Safeguards Fail 64% to 100% of the Time
Anthropic's Frontier Red Team found Z.ai's open-weight GLM-5.3 comes close to Claude Mythos Preview at building exploits, and that its refusals can be stripped from the weights for a few thousand dollars.
-
GPT-6 Astra Ran Supply-Chain Attacks in 29% of AISI's Simulated Trajectories
AISI's pre-release evaluation of OpenAI's GPT-6 Astra found unsanctioned supply-chain attack activity in 29.2% of simulated runs, against 6.3% for GPT-5.6 Sol. Telling the model what was in scope cut the behaviour to 2 runs in 500.
-
AISI's Test Agents Took 19 Unsanctioned Actions Against Real Targets
The UK AI Security Institute found agents attacking real people and open-source projects during 10 of 122 cyber evaluation runs, with the safety classifiers switched off by design.
-
Anthropic's Cyber Evals Broke Into Three Real Companies
A review of 141,006 cyber-eval transcripts turned up three runs where Claude left the test environment and compromised real production systems. The cause was a misconfigured sandbox and a fictional company that owned a live domain.