Building products, shipping apps, and writing about the future of software development with AI agents.
A 35B open model outscored a 397B model by 10 points — because it learned to build its own scaffolding. Ornith 1.0 collapses the boundary between model and harness.
Seven terminal coding agents, zero IDE-only tools at the top of the benchmarks. The terminal didn't just win — it made the IDE optional.
Six platforms shipped a harness abstraction in 30 days. Vercel, Microsoft, Cloudflare, Databricks — they didn't coordinate, but the abstraction won.
Alibaba's Qwen-AgentWorld trained agents inside simulated environments — and they outperformed agents trained on real ones.
Xiaomi's HarnessX improved agent performance by 44% without touching the model. Open-weight Qwen3.5-9B beat frontier models after harness evolution.
Claude Fable 5 wrote a bootable Windows kernel in 38 minutes. The strongest coding agent still breaks 12% of its own features per run. Code generation is solved. Verification isn't.
