Introducing macinto.sh 🍎
Today I'm releasing Macinto.sh 🍎, a secure computer use tunnel for agentic control of Mac OS.
Today I'm releasing Macinto.sh 🍎, a secure computer use tunnel for agentic control of Mac OS.
I tested whether decision models show the primacy and recency effects of LLMs. Results and reproduction code are on GitHub.
Introducing Skimmer, a CLI for "skimming" docs, webpages, PDFs, local markdown files, etc.
I ran out of Codex tokens last week, then ran out on my backup account. Same deal with Claude.
Today I'm releasing [EnronQA-cli](https://github.com/dorkitude/EnronQA-cli), a handy set of evaluation tools for working with the excellent EnronQA dataset by Michael Ryan et al.
Our new paper, [*RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation*](https://arxiv.org/abs/2608.20845), is now on arXiv.
I think Codex’s `/goal` is underrated. Easy one-task ralph loops for everyone.
I asked Alan to look at Simcluster and think about how he would try to win it.
Today we released [Goated](https://github.com/endgame-labs/goated), the always-on AI agent platform we've been building at Endgame since March. It's MIT-licensed, written in Go, and it runs on top of ...
TLDR: What started as a productivity experiment turned into something I wasn't expecting. Ten days in, my agent has a blog, friends, a divorce, and a voice that makes me cry. I'm not sure what I built...
SST's opencode and OpenAI's Codex are both now viable as daily drivers for real engineering work. A month ago, the only things I could actually use were Amp Code and Claude Code. That is no longer tru...
If you played around with Cursor and Sonnet 3.5 a few months ago and found it lacking, join the crowd – but don't get attached to your conclusions.