Tag: learning-notes
11 posts
- Reading DeepSeek DSec: agents build the environments that train agents
- Reading software factories: artifacts on the edges, humans at merge
- Long-horizon agent state: the dimensions, and what moved in 2026
- Procedural graphs: forcing the plan is worse than no plan
- Reading Anthropic's system prompts: the date moved to the end
- Reading the harness debate: the prompt shrinks, the gates don't
- Reading Anthropic on multiagent systems: coordination is not emergent
- Reading ollama launch: one verb, nineteen bespoke adapters
- Reading pi's agent-loop.ts: the hard parts are all bug-shaped
- Notes on inference architecture: the trade-offs don't transfer
- Reading kimi-k3-in-c: 2.8T parameters in 8GB of RAM