http://localhost:3000/notes http://localhost:3000/graph http://localhost:3000/about 2026-08-29T00:00:00.000Z http://localhost:3000/notes/benchmarking-your-own-agent-spend 2026-09-04T00:00:00.000Z http://localhost:3000/notes/gpt-6-astra-automated-ai-engineer 2026-09-04T00:00:00.000Z http://localhost:3000/notes/keeping-an-agent-running 2026-09-04T00:00:00.000Z http://localhost:3000/notes/agentic-engineering 2026-09-01T00:00:00.000Z http://localhost:3000/notes/code-is-not-cheap 2026-09-01T00:00:00.000Z http://localhost:3000/notes/deep-modules-and-agent-legibility 2026-09-01T00:00:00.000Z http://localhost:3000/notes/harness-engineering-agent-first-repositories 2026-09-01T00:00:00.000Z http://localhost:3000/notes/linting-as-agent-guardrail 2026-09-01T00:00:00.000Z http://localhost:3000/notes/loop-engineering 2026-09-01T00:00:00.000Z http://localhost:3000/notes/ubiquitous-language-for-agents 2026-09-01T00:00:00.000Z http://localhost:3000/notes/learning-from-deployment 2026-08-30T00:00:00.000Z http://localhost:3000/notes/model-speciation-and-touching-the-weights 2026-08-30T00:00:00.000Z http://localhost:3000/notes/model-training-as-code 2026-08-30T00:00:00.000Z http://localhost:3000/notes/prague-training-harness-talk 2026-08-30T00:00:00.000Z http://localhost:3000/notes/auto-research 2026-08-17T00:00:00.000Z http://localhost:3000/notes/diffusion-versus-autoregressive-generation 2026-08-17T00:00:00.000Z http://localhost:3000/notes/inference-engineering-baseten 2026-08-17T00:00:00.000Z http://localhost:3000/notes/recursive-self-improvement-greenblatt 2026-08-17T00:00:00.000Z http://localhost:3000/notes/training-and-inference-are-merging 2026-08-17T00:00:00.000Z http://localhost:3000/notes/aligned-to-whom 2026-08-14T00:00:00.000Z http://localhost:3000/notes/data-versus-architecture 2026-08-14T00:00:00.000Z http://localhost:3000/notes/jaggedness-and-what-rl-optimises 2026-08-14T00:00:00.000Z http://localhost:3000/notes/optimising-for-the-benchmark 2026-08-14T00:00:00.000Z http://localhost:3000/notes/sutskevers-list-notes 2026-08-14T00:00:00.000Z http://localhost:3000/notes/too-dangerous-to-release 2026-08-14T00:00:00.000Z http://localhost:3000/notes/training-against-your-own-monitor 2026-08-14T00:00:00.000Z http://localhost:3000/notes/containerising-ai-research 2026-08-13T00:00:00.000Z http://localhost:3000/notes/generator-evaluator-loops 2026-08-13T00:00:00.000Z http://localhost:3000/notes/self-improving-agents-from-production-feedback 2026-08-13T00:00:00.000Z http://localhost:3000/notes/separating-drafting-from-judging 2026-08-09T00:00:00.000Z http://localhost:3000/notes/writers-on-starting-finishing-and-bad-drafts 2026-08-09T00:00:00.000Z http://localhost:3000/notes/doordash-on-agentic-commerce-and-dot 2026-07-30T00:00:00.000Z http://localhost:3000/notes/the-claw-layer 2026-07-28T00:00:00.000Z http://localhost:3000/notes/the-customer-is-not-the-human 2026-07-28T00:00:00.000Z http://localhost:3000/notes/the-last-hundred-feet 2026-07-28T00:00:00.000Z http://localhost:3000/notes/building-a-generator-evaluator-harness-plan 2026-07-27T00:00:00.000Z http://localhost:3000/notes/harness-design-for-long-running-coding-agents 2026-07-27T00:00:00.000Z http://localhost:3000/notes/harness-design-reading-list 2026-07-27T00:00:00.000Z http://localhost:3000/notes/skill-issue-karpathy-on-code-agents 2026-07-27T00:00:00.000Z http://localhost:3000/notes/the-harness-is-a-skill-issue 2026-07-27T00:00:00.000Z http://localhost:3000/notes/agentic-engineering-my-role-in-the-loop 2026-07-26T00:00:00.000Z http://localhost:3000/notes/llm-wiki-pattern 2026-07-26T00:00:00.000Z http://localhost:3000/notes/tabular-foundation-models-notes 2026-07-17T00:00:00.000Z http://localhost:3000/notes/llm-customization-and-fine-tuning-notes 2026-07-15T00:00:00.000Z http://localhost:3000/notes/serving-slms-on-a-desktop-gpu 2026-07-14T00:00:00.000Z http://localhost:3000/tags/agentic-engineering http://localhost:3000/tags/harness-design http://localhost:3000/tags/evaluation http://localhost:3000/tags/ai-safety http://localhost:3000/tags/inference http://localhost:3000/tags/reading-notes http://localhost:3000/tags/deep-learning-history http://localhost:3000/tags/deployment http://localhost:3000/tags/fine-tuning http://localhost:3000/tags/recursive-self-improvement http://localhost:3000/tags/reward-hacking http://localhost:3000/tags/agentic-commerce http://localhost:3000/tags/ai-policy http://localhost:3000/tags/code-quality http://localhost:3000/tags/frontend-design http://localhost:3000/tags/hands-on http://localhost:3000/tags/linting http://localhost:3000/tags/robotics http://localhost:3000/tags/scaling http://localhost:3000/tags/talks http://localhost:3000/tags/writing-craft http://localhost:3000/tags/code-review http://localhost:3000/tags/knowledge-management http://localhost:3000/tags/reading-list http://localhost:3000/tags/tabular-foundation-models