From July through November, Moore's team sent roughly two million prompts to AI services. Each prompt carried its own AWS key, DNS name, URL or other secret that had never been used anywhere else, and the team ran the servers those…
In the News: November 21, 2026 (Morning)
HD Moore seeded about two million prompts with trackable secrets and watched AI providers, resellers and attackers use them.
Two million bait prompts show inference data leaking through routers, resellers and breached providers
Hugging Face trains one LoRA per coding harness and cuts tool calls by more than half
The team froze Qwen3.8-27B and trained a separate LoRA adapter for each of three agent harnesses, pi, Hermes Agent and OpenCode, with reinforcement learning run inside the unmodified harness. A proxy between the harness and the inference…
SpecBench: A tool to evaluate AI-enabled software development workflows
In one sample run per workflow under the same model label, a spec, plan and decompose workflow raised mean behavioral correctness from 92.25% to 95.00% over direct implementation. It also roughly doubled time (83.74 to 163.93 minutes) and used about four times the tokens (450K to 1,782K). The authors call this descriptive evidence from limited cases, and no harness or data is linked.