Teaching nanochat to count r's in strawberry
A full guide to adding a capability to a tiny LLM: synthetic tasks, tokenization traps, and why a honeybee-sized model needs the data over-represented.
Related reads
The Agents CLI in 30 minutes
@svpino
Santiago on the Agents CLI. Build, deploy, and watch a small multi-agent system without the usual harness ceremony.
Sep 16, 2026
AI-native thinking
@dotey
Baoyu's Tencent talk. Find demand on the model capability line, kill bad ideas with prototypes, then redesign so the agent verifies itself.
Sep 2, 2026
Worktrees and coding agents
@davidgomes
David Gomes on harness-managed git worktrees versus letting the agent own the tree. The second one tends to become abstract art.
Aug 29, 2026
What happens when a GPU writes memory
@finn_fergus
Fergus Finn follows an RTX 4090 STG.E from the warp through L1, L2, dirty lines, write-back, and DRAM. The store finishes in 6 cycles. The data gets to DRAM later.
Aug 29, 2026
