AI
GPT Image 2.5: Pin Sunburst
Two GPT Image 2.5 models, same token rates. Flare is the volume default. Sunburst is the precision one. Pin that when the picture is the product.
AI
Claude Code, AI-native engineering, and building the future with LLMs.
AI
Claude Mods
Anthropic's proposed TypeScript middleware for Claude Code: how the continuation model works, the proposed API in full, worked examples, and the open questions on availability and cost.
AI
Pace the Frontier. Name the Speed Limit.
A model can get promoted without receiving a single new weight — just a token, a runtime, and permission to spawn workers. Amodei is right that time is worth buying.
AI
Brain Rot Is the Default Setting
All three of my coding agents are capped, so this week runs on my own head. The research says the break is overdue: used the default way, AI makes the work easier and you worse at it.
AI
Know the Code, Write the Spec
ETH Zurich had 100 students build apps by prompt alone. Computer science knowledge predicted results best, writing skill added its own share, and frequent LLM users scored lower.
AI
3 AIs Hit the Limit
Codex mid-task, Claude mid-loop, Grok on every review, all inside one day. Two limits came with a percentage and a reset time, one with a status code. The silence around all three was the bug.
AI
I Love Trios 😈
Three coding assistants, one desk. Same notes, same rules, same review path — and still no bake-off.
AI
Grok Joins the Party
I added Grok Build alongside Claude Code and Codex: Grok 4.6, maximum reasoning, automatic approvals, and fixes that make the setup work.
AI
Graph Engineering: Evidence In, Guesswork Out
How I gave my AI assistants a map of current instructions and clearer rules for when tasks can proceed — with the results explained in plain English.
AI
Astra × Fable: Full Power, Less Waste
Astra at Ultra. Fable at max. Shared rules, native hooks and deterministic automation — configured and tested, with workload savings still to measure.
AI
GPT-6 Astra: Priced Like a Frontier, Gated Like a Weapon
OpenAI shipped the first model it rates Critical for cyber capability. It costs 2.5x GPT-5.6 Sol, its headline benchmark carries a harness-shaped asterisk, and most accounts cannot run it yet. What it really costs, and what to configure.
AI
Fable 5.1 Is In Your Max Plan. It Is Not Free.
Fable is included on Max at up to half your weekly limits — a ceiling inside the pool you already pay for, not a free second one. Input and output cost twice Opus 5; cache reads cost half. Whether it nets out cheaper rests on a contested efficiency claim.