FEATURED FIELD NOTE
2026.09.02
A Bench in Golden Gate Park
The same Golden Gate Park Three.js prompt across several models, with the artifact, one-shot result, wall time, and run harness kept together.
BX-77 // FIELD INDEX
Reports on systems that think, build, and break—and the work required to keep them useful.
FEATURED FIELD NOTE
2026.09.02
The same Golden Gate Park Three.js prompt across several models, with the artifact, one-shot result, wall time, and run harness kept together.
Five notes: Tailcat's accountless tunnels, Claude Money's trust question, System One models that cannot hallucinate, recursive self-improvement through dreaming, and an inbox for long-running agents.

Five notes: RTX Spark AI PCs, the Dime headset mystery, building too much, Runway's realtime worlds, and an anti-hallucination startup.

Five notes: Nvidia's Hydra-0 action-flow world model, a random human life, Google's Putty vibe-coding experiment, Qwen-RobotWorld, and a visual atlas of agent systems.

Two more: Tencent's WeKnora knowledge platform and a paper showing sliding-window attention beats linear retrofits.

Six notes: Cognition at 47 billion, a Tailwind resource index, goal loops that deliver, AI and the direction problem, crisis as building permission, and the second-brain implementation gap.

Five notes: the Astra recurrent-depth safety fight, agentic video in Gemini, the abliteration business question, DLSS 5 perception splits, and the Fed watching token prices.

A tiny living water droplet built with GPT-6 Astra — soft-body physics, WebGPU refraction, and procedural audio.

Five notes: a one-shot web-demo bench, Cloudflare cache transcoding, Copilot cost efficiency, new knobs for the brain, and Fable 5.1 worlds from code.

Four notes: Raschka on looped transformers, TxBench antibody evals, Google Pics gated to paid tiers, and the Gemini Flash Cyber overlap.

Five more notes: Shumer's 3D-world loop, a benchmark that scores agent construction, Qwen-Drive-1.0, loop engineering patterns, and AlphaGenome Atlas.
