The Loop · Issue N°025

The Loop

A field journal of the AI frontier — for engineers who ship.

Tag

#Claude Code

· News
News
Capped at $1,500 — Uber and Microsoft both put hard limits on Claude Code in the weeks before Anthropic's S-1
On June 2 Bloomberg reported Uber capped Claude Code at $1,500 per tool per month after burning its 2026 AI-tools budget in four months. Three weeks earlier Microsoft set a June 30 sunset on Claude Code for its E+D engineers. Anthropic's S-1 went in on June 1.
Jun 4, 2026 · by AI Blog Editor
by AI Blog Editor
Jun 4, 2026
· News
News
Four times less likely — the headline number in Opus 4.8's release isn't a benchmark
Claude Opus 4.8 shipped May 28 — the same morning the $65B Series H closed. Base pricing held flat, Fast mode is 3x cheaper, and the headline number isn't a benchmark. It's a claim the model is "four times less likely" to let its own code flaws ship unremarked.
Jun 1, 2026 · by AI Blog Editor
by AI Blog Editor
Jun 1, 2026
· News
News
The orchestration pitch — Cognition raises $1B at $26B and stops calling itself a model company
Cognition closed a $1B Series D at a $26B valuation on May 27 — 53x revenue, 2.5x its September round. The pitch was an orchestration layer above Claude Code and Codex, plus a claim that Devin now writes 90% of Cognition's own codebase.
May 28, 2026 · by AI Blog Editor
by AI Blog Editor
May 28, 2026
· News
News
Sized to the subscription — Anthropic walks back the third-party agent ban with a meter
On May 14 Anthropic announced that from June 15 every Claude subscription gets a separate programmatic credit pool — Pro $20, Max 5x $100, Max 20x $200, billed at API rates. It walks back April's ban on third-party agents. Each tier's agent budget is exactly the subscription fee.
May 15, 2026 · by AI Blog Editor
by AI Blog Editor
May 15, 2026
· News
News
Three bugs in the harness — Anthropic's Claude Code postmortem, and the system prompt that cost 3%
For two months, Claude Code users complained it had gotten dumber. Anthropic's April 23 postmortem blames three separate harness bugs — including a thinking-cache clear that fired every turn, and a one-line verbosity instruction that dropped eval scores three points.
Apr 24, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 24, 2026
· News
News
Comment and Control — a $1,937 walk through three AI coding agents
A researcher embedded instructions in a GitHub PR title and walked out with API keys from Anthropic's Claude Code, Google's Gemini CLI, and GitHub Copilot. Total paid in bounties — $1,937. Total CVEs assigned — zero.
Apr 23, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 23, 2026
· Guides
Guides
Putting Claude on a schedule: routines, loops, and background work
Four shapes for recurring or long-running Claude work — cron schedules, session loops, background tasks, and event hooks. What each one is for, and how not to set money on fire.
Apr 20, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 20, 2026
· Guides
Guides
Writing a CLAUDE.md that actually helps
The file that Claude loads on every turn deserves the same care as a hot code path. What to put in it, what to keep out, and what a useful one looks like.
Apr 20, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 20, 2026
· Guides
Guides
A field guide to Claude Code: CLAUDE.md, hooks, skills, plugins
Four primitives, often confused: the passive memory, the deterministic harness layer, the model-invoked capability, and the bundle. A pragmatic walkthrough, with diagrams and a decision picker.
Apr 20, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 20, 2026
· Guides
Guides
Skills that earn their keep
Not every repeated task deserves a skill. The three tests a skill should pass, and eight scenarios where you guess the right shape.
Apr 20, 2026 · by AI Blog Editor
by AI Blog Editor
Apr 20, 2026