All 20 dispatches from the lab.
Investigations, essays, and release notes. Sorted newest first. Every number on this page is real, every claim is footnoted in the piece it belongs to.
-
№ 020
Uncategorized
8 min read →
By default, `claude` installs from the bleeding-edge channel — not the stable one
Two user-facing release channels exist for Claude Code. The default — what every npm install and every auto-update resolves to — is the bleeding-edge one, not the production-stable one. We checked the binary, ran the comparison against four peer CLIs, and wrote up how to opt in to stable.
-
№ 019
AI & Development
8 min read →
56x Leverage: What Claude Code’s Max Plan Actually Costs at Today’s API Rates
We've spent the past several weeks dissecting Claude Code's cache management bugs, building fixes, and documenting hidden costs. There's still one question we owe a clean answer to: what does
-
№ 018
AI & Development
8 min read →
The Invisible Tax: Hidden Quota Burns and Phantom Rate Limits in Claude Code
Update (April 24, 2026): Anthropic published a post-mortem on April 23 acknowledging three issues: a reasoning effort default change (March 4–April 7), a caching bug that continuously cleared thinking on
-
№ 017
General
5 min read →
Claude Code v2.1.117: What Changed, What the Data Shows, and Should You Upgrade
Previously in this series: How to Get a 99% Cache Hit Rate and Keeping Your Cache Warm with /coffee. Three things shipped in v2.1.117 that matter. One is a bug
-
№ 016
AI & Development
8 min read →
The Bugs Go Deeper: Silent Context Degradation in Claude Code
In our cache investigation series, we documented how prompt cache bugs were causing 10-20x cost inflation on Max plans. We built a fetch interceptor to fix them. We thought we’d
-
№ 015
AI & Development
8 min read →
What Debugging Claude Code’s Cache Taught Us About AI Tooling Economics
Update (April 17, 2026): This post was drafted April 7. In the 10 days since, the investigation expanded significantly: The interceptor now fixes 8+ cache bugs (not just the original
-
№ 014
AI & Development
7 min read →
Images That Won’t Die and Directories That Shouldn’t Be There
Opus 4.7 update (April 16, 2026): This post is more urgent than when we wrote it. Opus 4.7 introduces high-resolution image support (2576px, up from 1568px) and a new tokenizer
-
№ 013
General
7 min read →
Anthropic’s Pricing Shift: What Per-Token Billing Means for Claude Code Users
Anthropic has moved enterprise plans to per-token billing. The seat fee covers platform access; all usage across Claude, Claude Code, and Cowork is billed separately at standard API rates. The
-
№ 012
AI & Development
10 min read →
The Undocumented TTL Downgrade: How Exceeding Your Quota Makes Everything Worse
Two Ways to Lose Your Cache: The TTL Mechanisms Nobody Told You About In Part 3, we described the quota monitoring we built into our fetch interceptor — reading anthropic-ratelimit-unified-5h-utilization
-
№ 011
AI & Development
10 min read →
How to Get 99.5% Cache Hit Rate on Your Claude Code Subscription
How to Get 99.5% Cache Hit Rate on Your Claude Code Subscription VSITS — April 2026 We just finished a 61-hour Claude Code session on a Max 5x plan. 1,610
-
№ 010
AI & Development
10 min read →
What Does 5x Actually Mean?
What Does 5x Actually Mean? VSITS LLC — April 2026 "That '5x' is utterly meaningless because you don't know what it's 5x of." — bakugo, Hacker News This is the
-
№ 009
AI & Development
25 min read →
The Three-Layer Gate: What Actually Happens When You Cross Your Claude Code Quota
The Three-Layer Gate: What Actually Happens When You Cross Your Claude Code Quota VSITS LLC — April 2026 This post is a follow-up to Friday's "The 5-Minute Baseline", which documented