Blog
Yearly technical notes, benchmark case studies, and local-first AI systems work.
2026
How Scaling a Diffusion-LM made it worse
A human-directed, DeepSeek-executed experiment found that an 8M-parameter diffusion language model beat a 46.5M version on held-out riddles.
How I Beat Anthropic's 1,487-Cycle Benchmark with Claude and Codex
A human-directed, AI-assisted optimization session reached 1,469 cycles on Anthropic's open performance challenge while preserving correctness and keeping the implementation private.
Random Project of the Week: GitVisual
A quick build note on turning hundreds of GitHub stars into an interactive treemap with Codex.
Breaking into Y Combinator: Part 3 | The Hardening Loop That Made Codex Fail
Part 3: the C++ heat-diffusion task that completed the hardening loop, and the first time Codex failed cleanly.
Breaking into Y Combinator: Part 2 | Thermal Stack Calibration TB3
Part 2 of the benchmark design series: moving from a retrieval task that was too easy to inspect into a coupled thermal-stack calibration task that both Codex and Claude failed cleanly.
Breaking into Y Combinator: Part 1 | Hybrid Retrieval Fusion
A focused writeup on the Hybrid Retrieval Fusion TB3 task: its design, verifier strategy, iteration loop, and why the model failures were not strong enough.