Notes on the Software Factory
Notes from a talk on vibe coding: giving agents tools, speeding up the bottleneck, critics, memory, skills, integration tests, and the agent native stack.
Benedict Brady
Research on DeFi, Solana market structure, and LLM-assisted development.
Latest posts
Adapting Robotics Models for Chess
Fine-tuning π0.5, the open-source VLA from Physical Intelligence, to play chess on a 5 DOF arm, and ablating how much it really understands about the board, colors, and pieces.
Notes on Robotic Manipulation
Working up the robotic control stack from the lowest level: brushless motors, the torque loop, the velocity loop, and the position loop.
Notes on Foundation Models
A cross-disciplinary survey of foundation models, motivated at a high level of abstraction: VLMs, realtime interaction models, VLAs, image and video generation, world models, and biological foundation models.
A Review of GPT 5.5
Revisiting private frontier benchmarks (philosophy, negotiation, chess) for the GPT 5.5 release.
A Review of Opus 4.7
Revisiting private frontier benchmarks (chess perception, chess bench, negotiation, Optimization Arena) for the Opus 4.7 release.
Analyzing Chess Input Modalities
Analyzing how different input modalities (FEN, PGN, board images) impact frontier LLM chess ability.
Benchmarking Frontier LLMs on Negotiation
Testing how frontier LLMs negotiate by pitting them against each other in a resource-splitting game across thinking levels, model sizes, and providers.
Learnings from Optimization Arena
Three lessons from building and running Optimization Arena: robust verification, bottleneck identification, and inner vs. outer loop optimization.
Benchmarking Frontier Models on Chess
A comprehensive chess benchmark testing frontier LLMs on endgames, puzzles, and full games against Stockfish.
Closing the Software Loop
How coding agents are changing software development, from feature requests to autonomous deployment with minimal human intervention.
Building a Router with Claude
A walkthrough of building a multi-DEX router using Claude. Covers smart order routing across Orca, Raydium, Meteora, and Pump AMM.
Building a Prop AMM with Claude
Designing and deploying a proportional AMM on Solana using Claude Code and Opus 4.5. Includes live demo with real trading.
Predictions for 2026
24 predictions covering crypto assets, DeFi applications, infrastructure, Solana ecosystem, and AI developments.
Payment for Order Flow on Solana
In-depth analysis of how applications monetize user orderflow on Solana through fees, transaction tips, and market maker access.