Ai
9 entries
three.js — The Basics, and Why It Fits AI Work
three.js basics, a single-file setup, and the features you use most. Also embedding visualization, viewing 3D model outputs, and the errors AI-written three.js code …
Saving Tokens in Claude Code — Measured
I measured common Claude Code token-saving tips with claude -p: CLAUDE.md length, how you hand over logs, clearing sessions, model and effort, MCP tools, and subagents.
Claude Opus 5.5 vs GPT-6 Sol — Cost, Performance, Coding Agents
Claude Opus 5.5 and GPT-6 Sol shipped 90 minutes apart on September 22. Sol is exactly half the per-token price, but cost per task, coding agent scores and the 272K …
Orca — An Agent Development Environment for Running Agents in Parallel
An open-source ADE that isolates CLI coding agents like Claude Code and Codex into separate git worktrees so they can run at once. Install, the worktree dependency …
GPT-6 Astra vs Fable 5.1, Opus 5 and GPT-5.6 Sol
GPT-6 Astra shipped on September 3. Compared against Claude Fable 5.1, Opus 5 and GPT-5.6 Sol: the 2.5x price increase, the token-efficiency twist, the ARC-AGI-3 harness …
Claude Fable 5.1 vs Opus 5, Fable 5 and GPT-5.6 Sol
Claude Fable 5.1 shipped today. Compared against Opus 5, Fable 5 and GPT-5.6 Sol: the 75% cache-read price cut, three breaking changes, and where the vendor table and …
LLM Wiki — Compiling Knowledge Instead of Re-reading It
A walkthrough of Karpathy's LLM Wiki pattern: the three-layer structure, the ingest/query/lint loop, how people actually use it, and how much of the efficiency claim has …
The San Francisco AI Declaration, Summarized
What the San Francisco AI Declaration of July 24, 2026 actually says, which deals were signed alongside it, and what Korea's AI Framework Act requires from developers …
Claude Opus 5 vs GPT-5.6 Sol, Fable 5 and Sonnet 5
Claude Opus 5 compared with GPT-5.6 Sol, Fable 5 and Sonnet 5 across coding, agentic work, long context and cost, plus what changed from Opus 4.8 and what to watch when …