The Cost Control Plane

Measure AI cost per accepted outcome, normalize usage telemetry, evaluate caching and routing, and enforce budgets without assuming a universal optimization order.

The Fable Tax

A July 2026 analysis of proposed Fable metering, subsequent changes, and the distinction between subscription access and API pricing.

Make Love Not War

Two rival frontier models, both at maximum reasoning, in one autonomous engineering loop. Why independent review, observability, and verified output matter more than picking a side.

Sol Ships: GPT-5.6 and Lower API Rates

GPT-5.6 launched July 9, 2026. Sol’s launch rates were 50% lower for input and 40% lower for output than Fable 5; benchmark and configuration claims need their exact scope.

J-Space: The Silent Workspace Inside Claude

Anthropic found a small, privileged workspace inside Claude — internal patterns, readable with a new Jacobian 'J-lens', holding concepts the model reasons with but never writes down. Not a consciousness claim. Maybe something more useful: a window into the thoughts a model doesn't print.

Sol, Terra, Luna: OpenAI Splits GPT-5.6 Into Three

Sol, Terra and Luna offer different capability and cost tradeoffs. A current API comparison of reasoning controls, token prices and workload evaluation.

Advisor and Executor: Using Fable 5 Without the Fable 5 Bill

Anthropic's ClaudeDevs shared the pattern they lean on with Fable 5: don't make the frontier model do the work — make it the advisor. A cheaper executor runs the loop and calls up to Fable 5 only at the decisions that matter. Most tokens bill at the cheap rate; judgment stays near the top.

GPT-Live: OpenAI Bets the Interface Is Voice

GPT-Live combines full-duplex voice with backend model delegation. How live conversation, tool permissions, interruptions and application state fit together.

The Making of Claude Code

Anthropic’s oral history traces Claude Code from early coding assistants and the internal clide CLI to a public product. Lessons in model capability, product design and feedback.

The Third Leash

An illustrative PATH wrapper selects an authorized Claude Code identity and model at process launch. Its scope, inheritance limits and failure policy explained.

The Loop Files Its Own Work

How an autonomous coding loop can discover missing work, track dependencies and verify live behavior. A hypothetical architecture with explicit authority, budgets and completion checks.

Fable 5 Comes Off the Leash

Anthropic's most capable widely released model was frozen by a US export-control order three days after launch. Eighteen days later the controls came off — and the reason it came back says more than the reason it left. The whole story, in one place.