In my last post, I shared an early prototype of Soma and argued why static .cursorrules and CLAUDE.md...
From Prototype to 1,890(Behavioral) Tests: Hardening an AI Agent Governance Engine
Related
Why LLMs Quietly Round Up Your Resume Metrics (And How I Blocked It Without Another LLM)
If you ask an AI to "tailor my resume to this job description without making anything up," it still...
OpenEnv + Agent Substrate: Run Agentic RL In Isolated Sandboxes
One of the most amazing advancements of Agents is that when you ask a question, it's not a "one...
I checked 33,204 x402 listings against the chain. The call counts held. The payer counts didn't.
The x402 discovery index lists 33,204 paid endpoints. I probed 269 of them and checked four payees against 30 days of USDC transfers on Base. The activity numbers hold up. The uniq...