Readable notes, essays, and summaries.
- Watching the solar eclipse from Dehesa Boyal
2026-08-12
#eclipse#dehesa-boyal#family
- Type it yourself: a deliberately slow workflow for AI-generated code
2026-08-03
#aisummary
Ankur Sethi uses an LLM to propose code in chat, then types every edit himself—trading maximal speed for comprehension, taste, and a durable mental map of the codebase.
- AI development in 2026 is a workflow problem, not a coding problem
2026-07-12
#aisummary
Notes from Kirill Mokevnin on the tools, workflows, metrics, and anti-patterns emerging as companies move from AI-assisted coding toward AI across the software-development lifecycle.
- Saturday thunderstorm
2026-07-11
#thunderstorm#saturday
Saturday thunderstorm.
- AI agents are easy to demo and hard to make real
2026-07-10
#aisummary
Andrej Karpathy on why OpenAI’s first computer-use agents failed, why model capability had to come first, and why agent builders should think in decades rather than demos.
- The dead economy: when automation destroys its own customers
2026-07-10
#aisummary
Owen McGrann’s dark but useful argument that AI automation can be rational for every firm and destructive for the economy they share.
- Finding your unknowns with Claude Fable
2026-07-06
#aisummary
Notes from Thariq's X Article on Claude Fable, unknown unknowns, blind-spot passes, prototypes, interviews, references, implementation notes, and why agentic coding is increasingly about discovering what the human has not specified yet.
- AI is getting good at math. The hard part is knowing what counts as progress
2026-07-01
#aisummary
Notes from Dwarkesh Patel's conversation with Grant Sanderson on AI math progress, IMO gold, Millennium problems, conjectures, definitions, Lean, learning, and why the human bottleneck may move from proving theorems to judging which ideas matter.
- Sunday walk in Dehesa Boyal
2026-06-29
#walk#dehesa-boyal
Sunday walk in Dehesa Boyal.
- OpenAI Codex and the new shape of product work
2026-06-29
#aisummary
Notes from Lenny's Podcast with Andrew Ambrosino on Codex, cheap implementation, taste, role collapse, dogfooding, product planning, and why the future of work may look less like chat and more like a home base for delegated action.
- AI as public infrastructure, not just another app
2026-06-27
#aisummary
Expanded notes from the Forbes interview with the Liberman brothers on AI monopolies, pension-fund capitalism, compute bottlenecks, Gonka, agents, chips, and public AI infrastructure.
- Slow down to speed up: AI and software engineering
2026-06-25
#aisummary
Notes from Gergely Orosz's talk on why AI makes code generation cheaper, but makes judgment, review, product thinking, and guardrails more valuable.