
Nicholas Oxford
863 posts

Nicholas Oxford
@ApolloToday
Be Happy. Husband. Future Father. Atlanta native. Babson / Georgia State. Serenbe.




The City in the Forest is incredibly unique, and I can’t think of another major city in the US that has that similar combo of high rises surrounded by tree canopies on all sides

You have got to be kidding me? We’re just paying for all kinds of Rick Jackson’s goodies! 🙄🤦🏻♀️😡 “We have tanning, uh, blow-drying, um, chiropractors, uh, uh, you know, dry cleaning services. We have a daycare center that's second to none, um, and only because the state and the feds are subsidizing it, which is ano- another subject, but I'm gonna take advantage of it.”




People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question: How would we build software in the future if tokens don't matter? We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference. We run codex on every commit to review for security issues (as it's far too easy to miss). We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues. We have agents that can recreate complex setups, spin up ephemeral crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR. There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews) We have codex running that scans comments for spam and blocks people. We have codex instances running that verify performance benchmarks and report regressions into Discord. We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them. We build clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions. We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities. All that automation allows us to run this project extremely lean.



@glcst Choosing Zig was the right call early on. I had to write tons and tons of code quickly. And I don’t think I would’ve been able to get as much done in other languages. Bun’s focus on ecosystem compatibility was way more impactful for adoption than implementation language though







America has its "fallen" regions, esp. in the Rust Belt, and its emptying rural areas, esp. in the high plains. But generally the experience of driving the country is the constant discovery of money and development in places that look like the middle of nowhere on the map.







New: @ServiceNow is the latest major public company to say it’s blown through its full year budget for AI coding tools from Anthropic in the first few months of 2026, just like @Uber CTO @praveenTweets said abt his company. “It’s a really hard problem,” CIO Kellie Romack said.















