#claude-code
- ds4 runs big open weights locally and speaks the Anthropic API
The part I care about is not the 284-billion-parameter model squeezed down to 2 bits. It is that ds4-server speaks the Anthropic API at…
- Livenerf: a day-0 baseline for the 'they nerfed it' argument
The 'they nerfed it' argument never ends because nobody has a day-0 baseline, so it's vibes versus vibes. What I like here is the…
- 150 Watt-hours per prompt
I ran Claude Code most of last week without once wondering what it costs in watts. Hausfather's number — 150 Wh per prompt against Altman's…
- Vomit pipes Claude's output through a second local model
I run Claude Code all day and I've stopped reading half of what scrolls past. A tool that pipes that output through a second local model…
- Claude Code Is On Top, Which Is Exactly Why I Keep It Replaceable
39 percent professional usage, up 21 points since January. I use Claude Code daily, so I'm inside that number, and the honest reaction…
- I Am the Weakest Part of My Own Permission Prompt
I click approve on agent commands all day. Turns out I'm bad at it. In a browser game where you play human-in-the-loop, 40,000 runs and…
- The bottleneck is me, not the model
The uncomfortable part of Goedecke's argument is that it explains my own logs. When I'm working on the Astro site or a Cloudflare Worker…