Seedling··12 min read
Coding Agents Are the Base Agent
A practical mindset for picking up coding agents, even if you don't code. Destinations, maps, tools, and why every other agent is a coding agent in disguise.
Yad Konrad
Applied researcher, comedian. Deep interest in meta problem solving, making machines write code that write code.
Start Here
Budding··9 min read
Coding Agent Cheat Codes
CLI flags, environment variables, and proxy tricks for agentic engineering (or vibe coding, whatever you call it)
Seedling··22 min read
58 Schmidhuber Papers in Pure NumPy with Claude Code
58 Jürgen Schmidhuber paper stubs implemented in pure numpy via the same SPEC-driven agent-team workflow, with the build internals now grounded in raw session data
Seedling··12 min read
Sutro Yaro: Agent-Driven Research on Hinton's Problems
How a SPEC issue, a wave of Claude Code agents, and GitHub PRs reproduced 53 Hinton experiments from 1981 to 2022 in one 49-hour run
Recent Notes
Seedling··11 min read
Building StackUnderflow: Local-First Observability for Coding Agents
A local-first toolkit that ingests session logs from 17 coding-agent providers to surface cost analytics, filesystem time-travel, and a session memory that agents can query mid-task. It answers two questions about your coding agents: what did this run actually cost, and what did I already learn here?
Seedling··12 min read
Coding Agents Are the Base Agent
A practical mindset for picking up coding agents, even if you don't code. Destinations, maps, tools, and why every other agent is a coding agent in disguise.
Seedling··22 min read
Building Chimera: A Coding Agent Framework, Built by Coding Agents
How building the same agent three times led me to decompose coding agents into composable primitives, and why I didn't write most of the code
Seedling··22 min read
58 Schmidhuber Papers in Pure NumPy with Claude Code
58 Jürgen Schmidhuber paper stubs implemented in pure numpy via the same SPEC-driven agent-team workflow, with the build internals now grounded in raw session data
Seedling··12 min read
Sutro Yaro: Agent-Driven Research on Hinton's Problems
How a SPEC issue, a wave of Claude Code agents, and GitHub PRs reproduced 53 Hinton experiments from 1981 to 2022 in one 49-hour run
Seedling··10 min read
Sutro Yaro: Agent-Driven Research on Energy-Efficient Learning
How a study group in San Francisco turned coding agents into research agents by going back to 1960s AI problems with modern tools
Seedling··6 min read
Building Mycelium: A Digital Garden Theme for People Who Actually Write
Why I built a digital garden theme around how I actually think and write
Seedling··15 min read
Building Bourbaki: A Math Agent That Can Check Its Own Work
How I built an autonomous agent for mathematical reasoning with SymPy, Lean 4, and structured proof techniques, and what I learned along the way
Seedling··8 min read
Make an Honest Resume for Your Coding Agent
Why giving your coding agent an honest map of what you know and don't know changes everything about how it helps you
Seedling··12 min read
Building Erdős Navigator: Claude Code as a Theorem Proving Assistant
How program synthesis led me down a rabbit hole through HoTT and algebraic topology, and back out through LLMs and a toolkit for 1,179 unsolved math problems
·Seedling·11 min read
Building StackUnderflow: Local-First Observability for Coding Agents
A local-first toolkit that ingests session logs from 17 coding-agent providers to surface cost analytics, filesystem time-travel, and a session memory that agents can query mid-task. It answers two questions about your coding agents: what did this run actually cost, and what did I already learn here?
·Seedling·12 min read
Coding Agents Are the Base Agent
A practical mindset for picking up coding agents, even if you don't code. Destinations, maps, tools, and why every other agent is a coding agent in disguise.
·Seedling·22 min read
Building Chimera: A Coding Agent Framework, Built by Coding Agents
How building the same agent three times led me to decompose coding agents into composable primitives, and why I didn't write most of the code
·Seedling·22 min read
58 Schmidhuber Papers in Pure NumPy with Claude Code
58 Jürgen Schmidhuber paper stubs implemented in pure numpy via the same SPEC-driven agent-team workflow, with the build internals now grounded in raw session data
·Seedling·12 min read
Sutro Yaro: Agent-Driven Research on Hinton's Problems
How a SPEC issue, a wave of Claude Code agents, and GitHub PRs reproduced 53 Hinton experiments from 1981 to 2022 in one 49-hour run
·Seedling·10 min read
Sutro Yaro: Agent-Driven Research on Energy-Efficient Learning
How a study group in San Francisco turned coding agents into research agents by going back to 1960s AI problems with modern tools
·Seedling·6 min read
Building Mycelium: A Digital Garden Theme for People Who Actually Write
Why I built a digital garden theme around how I actually think and write
·Seedling·15 min read
Building Bourbaki: A Math Agent That Can Check Its Own Work
How I built an autonomous agent for mathematical reasoning with SymPy, Lean 4, and structured proof techniques, and what I learned along the way
·Seedling·8 min read
Make an Honest Resume for Your Coding Agent
Why giving your coding agent an honest map of what you know and don't know changes everything about how it helps you
·Seedling·12 min read
Building Erdős Navigator: Claude Code as a Theorem Proving Assistant
How program synthesis led me down a rabbit hole through HoTT and algebraic topology, and back out through LLMs and a toolkit for 1,179 unsolved math problems
Featured Projects
View all →Novalis
A GPU-rendered terminal built for the way work looks when coding agents do half of it — agents get a cockpit, you keep the controls.
Rusteguiwgpu
staxtrace
Offline, local-first observability and memory for AI coding agents — cost analytics, time-travel playback, and a memory layer your agents query mid-task.
PythonSQLiteFTS5
Pacenote
An open-source Python framework for building coding agents. Pick your provider, pick your tools, pick your loop — then race whole agents against each other on the same task.
PythonCoding AgentsBenchmarks