Notes on building autonomy you can prove

A technical account of the mismatch between single-forward-pass interpretability methods and the failure modes of agents that plan, act, observe, and revise over many steps - grounded in published circuit-analysis literature, a controlled failure-attribution benchmark, and emerging graph-based tracing methods.

An industry-neutral engineering reference on containing agents that browse, execute code, and act on the open internet - synthesized from disclosed CVEs, published isolation-technology internals, OWASP's agentic risk taxonomy, and the operating architectures of production agent-sandbox vendors.

A methodological deep dive into why evaluation is not oversight, how the runtime-verification and machine-learning-monitoring traditions converge on autonomous language-model agents, and what the published, quantitative record says about how well post-deployment monitors actually work.

A technical breakdown of three verified, published research programs that used mechanistic interpretability, linear probes, sparse autoencoders, and residual-stream analysis, to detect deception, hidden reward-hacking objectives, and strategic underperformance in language models before those models reached real users.

A methodological deep dive into sparse dictionary learning for neural network interpretability, how sparse autoencoders (SAEs) work, what they have genuinely revealed, and the specific, measured costs that get quietly left out of the demo.

A methodological deep dive into how Anthropic's interpretability team traces the internal computation of large language models, what the resulting "attribution graphs" actually show, and the specific, documented ways the method fails.

A technical deep dive for engineers and researchers building oversight into agentic systems