#agent-observability

1 stories this week · 3 this month · 3 in 6 months · mostly security

Stories per day · 30 days

3 stories, newest first · one card per story

Laminar says the RL-trained model matches GPT-6-sol detection quality at 23 times lower cost on its benchmark.

The eBPF tool keeps causal labels on files and sockets, with average observation overhead below 8%.

Troy Hunt says recent breaches came from phone vishing, not AI, calling AI breach hype unsupported.

Stories tagged #agent-observability