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.

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.

Brain Rot Is the Default Setting

AI assistance can reduce practice when it replaces the thinking a task requires. Research points to task-specific risks and ways to preserve unaided skills.

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.

Handling AI Usage Limits and Clean Handovers

Detect provider usage limits, save verified task state, preserve stop markers and hand over cleanly without confusing account limits with model quality.

I Love Trios 😈

Three coding assistants, one desk. Same notes, same rules, same review path — and still no bake-off.

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.

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.

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.

GPT-6 Astra: Priced Like a Frontier, Gated Like a Weapon

GPT-6 Astra’s access, pricing and model settings need separate checks. Compare accepted-task performance and verify availability before changing configuration.

Fable 5.1 Is In Your Max Plan. It Is Not Free.

Fable is included on Max at up to half your weekly limits. Input and output cost twice Opus 5; cache reads cost half. Whether it is cheaper per accepted task depends on workload and an efficiency claim that needs testing.

The Popcorn Is Still Warm 🍿

Anthropic’s full MHS launch reveals a coalition across labs, robots, cameras and boards—with an open-source release planned after the private research preview.