9 min read
Claude Voice Mode Now Runs on Opus and Sonnet
Anthropic updated Claude's voice mode with Opus and Sonnet, mid-call model switching, and real actions in Gmail, Calendar,…
The Lab · Written in the open · Tagged AI Tools
Lab.
Working notes from the studio. The tools I build, the workflows I keep, the mistakes I paid for.
184 entries · latest 2026-09-11
9 min read
Claude Security: Anthropic's New Vulnerability Scanner
Anthropic shipped Claude Security in beta, a multi-agent scanner that turns vulnerability findings into reviewed patches inside Claude…
9 min read
Claude Blueprint: Why I Packaged 33 Days Into One Install
Claude Blueprint packages a full Claude Code setup, a CLAUDE.md template, 6 commands, 6 skills, and 3 hooks,…
10 min read
OhNine: Why I Built a Menu Bar App for Claude Limits
OhNine is a free menu bar app that tracks Claude session and weekly usage limits and warns you…
9 min read
RAXXO Studio: Turning One Video Into Three Platforms
Why one caption pasted everywhere underperforms, and what building a platform-aware caption tool taught me.
9 min read
The AI Week: Kimi K3 Tops the Code Arena, Gemini 3.5 Slips
Kimi K3 topped a coding arena, Gemini 3.5 Pro slipped, and OpenAI shipped GPT-Live. A builder's read on…
9 min read
Claude Reflect: I Audited How I Actually Use AI
Anthropic's new Reflect dashboard shows how you actually use Claude. I ran it on myself for a week,…
9 min read
Claude Artifacts Now Call Your MCP Connectors for Live Data
Claude published artifacts can now pull live data through each viewer's own MCP connectors, no backend required. What…
9 min read
The Claude Code Features I Started Using This Month
1M context Opus replaced my manual file-pasting ritual entirely
8 min read
Anthropic Pulled Fable 5 and Mythos 5: What the Ban Means
Anthropic disabled Claude Fable 5 and Mythos 5 on June 12 under a US export order over a…
9 min read
Why I Stopped Using Cursor for Production Code (And What I Use Now)
Cursor felt fast for prototypes but stalled on real production tasks
7 min read
Claude Fable 5 vs GPT-5.5 vs Gemini 3.1 Pro: Who Leads Now?
SWE-Bench Pro: Claude Fable 5 hits 80.3 percent, GPT-5.5 lands 58.6, Gemini 3.1 Pro 54.2