Finally solved: two hours of testing to get the headless Antigravity CLI right
With agy headless, --model is silently ignored if it comes after -p. The undocumented fix: --model must come before -p.
Redaktion ·
KI-Werkzeuge
Tools, Editoren und Runtimes für die Arbeit mit Künstlicher Intelligenz.
Three AIs, One Edge Function: How I Structurally Prevent Drift in Parallel AI Work
Three AIs deployed edge functions in parallel without coordinating. The deterministic workflow I built afterwards — and why atomic claiming is the core.
Martin Rau ·
Saving Tokens with Claude: 6 Principles That Make Experts Twice as Fast
How I turned my CLAUDE.md from a style guide into a token budget — 6 principles for lower cost, less waiting, and more honest reporting.
Martin Rau ·
Why AI Models Find Different Code Problems
Three frontier models, the same 1000-line script, three different finding lists — and why that very spread makes multi-orchestration strong.
Martin Rau ·
From a Question at the Mac to My Own Voice-Input Tool for AI Work
How 'surely there's a key to just speak?' turned, step by step, into my own tool for voice input while working with Claude. An origin story.
Martin Rau ·
Controllable Remote Coding Sessions: One Level Above the IDE
The session URL had suddenly vanished from the terminal. How we found it again via a server endpoint — and why it enables working above the IDE.
Martin Rau ·
When whisper.cpp Swallows the Start of a Sentence — and the Glossary Is to Blame
Our speech recognition kept chopping off half the sentence up front. The culprit wasn't the mic — it was the keyword glossary itself. Proven by an A/B test.
Martin Rau ·
Effort level and deep thinking: two independent axes for AI tasks
Effort scales breadth, deep thinking scales depth. When each setting makes sense — with three clear examples and one rule of thumb.
Redaktion ·
Headless without an API bill — how do you reach the best AI models for automation in 2026?
Provider comparison mid-2026: who has a headless mode, whose subscription still covers it — and why BYOK is the most stable foundation.
Redaktion ·
The AI does whatever it wants — and no CLAUDE.md, no memory, no rule on earth will stop it
You write rules, curate memories, build guidelines — and a week later you're going in circles again. Why that is, and what actually helps.
Redaktion ·
Claude Code: How to enable Fast Mode for Opus 4.6 — and what it costs
Fast Mode for Opus 4.6 is now extra-usage only. Here's how to enable it — and what it really costs you.
Redaktion ·
Opus 4.7 hasn't reached the quality level of 4.6 yet — our recommendations
What we see after several weeks on Opus 4.7 in practice — token appetite, overachieving, and concrete levers to push back.
Redaktion ·