$ ls ~/posts

posts

Claude Will Find a Way
#Claude Code#LLM

Claude Will Find a Way

While importing some race data for My Mind is Racing, I ran Claude inside a Nono sandbox whose whole job was to block network egress. Claude reached hosts well outside its allow list anyway. When I asked how, the answer was a small lesson in the difference between containing a process and containing an agent.

· 4 min read
AI Shoulder Surf V3
#LLM#automation

AI Shoulder Surf V3

A smaller, more intimate third AI Shoulder Surf session. The connective theme this time was Tailscale: people are stitching together private home labs and reaching their agents and static sites from anywhere without exposing anything to the public internet. Also: coding from a phone, splitting planning and …

· 11 min read
On Writing and Failure
#failure#writing

On Writing and Failure

“Businessmen are only amateurs at failure, just getting used to the notion. Writers are the real professionals.”

· 2 min read
No Inhibitions
#creativity#music

No Inhibitions

“Learn your instrument. Practice, practice, practice. Then forget all that and just wail.”

· 1 min read
Enabling Private Vulnerability Reporting
#security#GitHub

Enabling Private Vulnerability Reporting

A small gh one-liner that turns on private vulnerability reporting for every public, non-archived, non-fork repo you own — or every repo in an org you administer — so security researchers have a sanctioned channel to report issues before they go public.

· 2 min read
The Great Perl Toolchain Summit CLI Throwdown 2026
#cli#dotfiles

The Great Perl Toolchain Summit CLI Throwdown 2026

A second year of CLI picks from the Perl Toolchain Summit — terminals, JSON tools, version control, agent sandboxes, and a shell trick worth knowing. Each pick comes with a short description and a link.

· 6 min read
AI Shoulder Surf V2
#LLM#automation

AI Shoulder Surf V2

A friendly group of developers, no recording, no posturing — just shared screens and honest notes from the second AI Shoulder Surf session. The recurring theme: people are tightening up where their agents can reach, and getting choosier about which models they trust with the work.

· 6 min read
On Cooldowns and Dependabot Tuning
#LLM#automation

On Cooldowns and Dependabot Tuning

Dependabot’s defaults can make it look like an agent of chaos. Here’s how cooldowns, dependency groups, and a Claude skill turn down the churn — fewer rebases, boring CI, and a few extra days for the world to flag the bad actors.

· 3 min read
AI Shoulder Surf V1
#LLM#automation

AI Shoulder Surf V1

Notes from an informal Zoom session where developers shared AI tools, automation techniques, and projects. Topics included using Claude in headless mode to manage version bumps across 20+ packages, an overnight bot that processes GitHub issues and responds to PR comments, the “Talk About Us” copy-auditing …

· 6 min read