Boop is on External TestFlight
Boop — my local-first WHOOP strap to Apple Health utility — just got external TestFlight approval. Here's what it is, what it isn't, and where to join.
13
Latest
Recent essays — models, tooling, and product notes.
Archive
2026
6 posts
Gemini 3.1 Pro: Deep thinking is here
Daniel Ensminger explains why Google's new thinking_level API and massive 64K token output limit in Gemini 3.1 Pro simplifies AI reasoning.
Sonnet 4.6: My New Daily Driver
I’m switching my default model to Sonnet 4.6 after seeing its flagship-level engineering performance at a fraction of the cost.
Cursor 1.5: From Autocomplete to Architect
Cursor 1.5 moves beyond simple code prediction to a 'Thinking' paradigm that architects logic before writing a single line.
GPT-5.3-Codex: It finally feels like an agent
OpenAI's GPT-5.3-Codex marks a paradigm shift from simple autocomplete to a state-manipulating agent that actually understands the terminal.
Why I'm refactoring for Opus 4.6
Claude Opus 4.6 just dropped with a 1-million token context window and adaptive thinking, forcing a total rethink of how I build production AI agents.
OpenClawd: Sovereign AI without the setup headache
Daniel Ensminger's deep dive into OpenClawd’s managed runtime and its unique Markdown-based approach to persistent agent memory.
Archive
2024
2 posts
Roborock S8 MaxV
Ein Testbericht von Daniel Ensminger: Der Roborock S8 MaxV ist Marktführer mit 10.000 Pa Saugkraft und ReactiveAI 2.0 für höchste Präzision.
Dreame L20
Ein Testbericht von Daniel Ensminger: Der Dreame L20 revolutioniert die Kantenreinigung mit MopExtend™-Technologie und bietet Premium-Features zu fairem Preis.