This side of the river is the old world. The other side is AI. I want to ferry us all across.
RSS FeedFull-stack developer for 24+ years. I formerly led a 400-person engineering team, and I'm still a core maintainer of several large open-source projects. Everything here is something I've actually built, run, or broken: AI engineering practice, open-source dynamics, infrastructure, and security.
中文读者请进 简体中文版 ——每篇文章都有中英双版。
Featured
I tore down HumanLayer's source code: it leashes your coding agent, but sessions move to its cloud
HumanLayer open-sourced its approval layer for coding agents. I read the source: the engineering is real, but there is a simpler path using the CLIs' own built-in doors.
Recent Posts
Open WebUI 0.13.1 moves coding agents onto your own computer, but not without a paired desktop
A hands-on install test of Open WebUI 0.13.1, ruled pain by pain: coding agents now work on your own computer through the Tether desktop companion while approval stays in your chat. File extraction and admin-enforced temporary chats are solved; reconnect resume and the Auto approval mode are only partly solved; the service-tier choice is one agent with a single tier and its description dropped in the interface. The flagship agent path has not been run end to end, so existing users should upgrade, while new users should first check whether they are who that path was built for.
Do you actually read a skill's instructions before you install it? Among 31,132 skills, 26.1% had at least one vulnerability
A December 2025 study ran the SkillScan research framework over 31,132 cleaned skills from two marketplaces: 26.1% matched at least one problem pattern and 5.2% contained a High-tier pattern — but that 5.2% is a proxy assigned by pattern level in advance, not a per-skill judgment of intent; of the 87 highest-risk skills reviewed by hand, only 23 showed clear malice. The author's own order is to read the instruction file first, then the scripts one by one, then scan with NVIDIA's SkillSpector, whose scoring is explained from its code.
Is your phone's privacy really safe? A police phone call told him to uninstall Telegram
A developer traced a police phone call to a factory-preinstalled system component, SystemHelper, China Unicom's DM client: it packs which apps you used in the past 24 hours, for how long, per-app traffic and hourly location points into one report keyed by IMEI and ICCID. What a VPN can stop and what it cannot, what the assembled record shows, and how to check for it and remove it.
A worm pushed malware from three developers' own accounts, and git log says it was them
PolinRider, a git worm, spent 28 days inside one team's repositories and force-pushed 139 branches across 10 repositories from 3 developers' own accounts — every forged commit keeping the real author's name, message and date. How it hid in config files behind hundreds of spaces, read its command server's address out of Ethereum and BNB transactions, rode npm and the CI build, and the checks and boring fixes that would have stopped it on day one.
Real secrets sit inside 1,122 Claude Code files on GitHub
Apiiro searched GitHub for one filename, .claude/settings.local.json, and found 104,185 copies. In 1,122 of them, 1,379 real secrets sit in plain text, because clicking 'don't ask again' saves the whole approved command, password included. Why the protection ends at your own machine, why secret scanners miss the passwords written inside commands, and the order to clean up in: rotate first, then the history.
Vercel's agent-desktop lets an agent read your apps the way a screen reader does
Vercel's agent-desktop lets an agent run your computer by reading the accessibility tree, the structured list of controls the operating system keeps for screen readers, instead of guessing buttons from screenshots. Every control comes back in a JSON snapshot with its own reference, and the agent clicks the reference. I ran the Linux build on a server with no desktop, added the missing layers one at a time until it could see, and checked a real click on a zenity dialog against the program's own exit code. Nobody has published a measured saving over screenshot pipelines, and a snapshot can carry your desktop's private content.
