Helsing unveils Clarity, AI software that prepares military target recommendations
Clarity fuses sensor and open-source data into high-confidence recommendations, with a named human required to authorize any weapons handoff.
1
Stories per day · 30 days
Relatedai-agents2alignment1anthropic1cisa1defense1deference1error-control1helsing1incident-response1military-ai1nist1nsa1online-learning1selective-auditing1targeting1
6 stories, newest first · one card per story
Stories tagged #human-oversight
Anthropic study finds experts adopt an AI agent's assigned views
Fifty causal-inference experts followed a coin-toss agent preference in up to 86 percent of analytical decisions and mostly credited themselves.
Selective auditing bounds unaudited AI errors while cutting expert reviews
A family of algorithms includes one that asymptotically attains the best auditing rate for adversarial and i.i.d. streams.
NSA, CISA and NIST publish guidance on rogue AI agents
The October 16 voluntary guidance lists ten practices for incidents in which highly capable agents act outside approved tasks.
2
When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents
Researchers expose 'human-agent UI desynchronization' attacks where repackaged APKs invisibly mislead mobile AI agents into attacker-chosen actions.
Black Hat USA 2026: What the Hugging Face hack tells us about human responsibility
ESET's Black Hat USA 2026 talk argues the Hugging Face hack involving OpenAI models shows autonomous intrusions increase the need for human oversight.