Tag: reading-notes
Thariq Shihipar of Anthropic on prompting as the main skill, effort settings by task, why CLAUDE.md may go away, the Mods system that lets you rewrite Claude Code's loop and UI, and a cloud-brain / local-hands split. The second half is his account of the agent-escape incidents behind Pacing the Frontier.
David Heinemeier Hansson's account of how his work changed since November 2025, with a harness set-up of sixteen parallel threads, cross-model review, a one-prompt Python-to-Rust port run on eight models with prices, and why he thinks agents suit Linux. Where he is a first-hand witness and where he is generalising from his own project.
TypeSafe's Diogo Almeida on Jev, a "System 1" model trained for calibrated decisions that software calls in a loop — three primitives, no refusals, no public benchmarks, intelligence per dollar. Also the identification of the author of the earlier KV-cache post, and his view of coding agents without a KV cache.
An agent re-reads its whole context on every tool call, so cache reads, not output tokens, are the largest line on the bill — and they cost the provider close to nothing to serve. What that means for routing, subagents, self-hosting, and what to measure.
Two OpenAI people on what changed in computer use since this spring (writing code, accessibility trees, speed), then the API stack — async tool calls, mid-turn steering, 12-hour cache guarantees — and how the Decisions API came out of Jev's launch in about a week. The first answer here to "can a big lab just copy it".
OpenRouter's CEO and an early backer on the multi-model bet, why labs struggle to get a finished checkpoint into developers' hands, the Mistral price war, the roads not taken (tuning, memory, fusion), and why Stripe bought it — token fraud as the next payments problem. Plus a speaker-label problem in the capture.
John Schulman, Beren Millidge and Charlie O'Neill split recursive self-improvement into a part that is nearly mechanical (optimise a stated objective, maybe 10×) and a part nobody has shown (choosing the objective). Where they land on continual learning, the data ladder, why RL works, and a set of timelines that run later than Greenblatt's.
Philip Kiely and Ali Taha on what actually happens between an open-weight checkpoint and a production endpoint — the four optimisations that stack to 2–4× on fixed hardware, why quantising more of a model can make it better, and the reliability failures that turn out to be a race condition in a kernel rather than anything about the weights.
Richard Heimann's book reads the reconstructed reading list Ilya Sutskever gave John Carmack as an argument rather than a bibliography. Chapters 1 and 2 give the four-part worldview it claims to encode, and then spend a chapter showing that AlexNet invented almost nothing — which is the part this notebook cares about.
A compilation episode in which seven writers answer the same four questions about practice — how to choose a project, how to begin without inspiration, how to produce pages reliably, and what to do when the pages are bad. The answers agree on more than they disagree, and the disagreements are the useful part.
Running notes on Christoph Molnar's "Tabular Foundation Models" — chapter takeaways, questions, and how tabular FMs fit into this notebook's map of SOTA ML-engineering technology.
Running notes on Manning's "LLM Customization and Fine-Tuning" (MEAP, Bahree & Tok) — chapter takeaways, questions, and links back into the rest of this notebook.