Jennifer Hull

@JennHull-builds

Design engineer who started building and never stopped. Mostly building tools to manage the other tools.

Commit activity

13 commits in the last year

longest streak 2 days

427 / 1,000 XP573 XP to wheel

Mon, Nov 9

Sun, Oct 25

replying to @0z3
Opus mainly, with strict tasks for Sonnet to execute. I have also started exploring GLM, DeepSeek, and Kimi models on my OpenCode plan recently, running a night shift on Github actions. I use Gemini a lot, but not for actual coding.

Fri, Oct 23

Wed, Oct 21

replying to @solomonneas
Evidence over trust is where I've landed too. One of my rules: a handoff from another agent is a guess until something proves it. When an agent receives an evidence package, does it re-check anything, or take the exit codes as proof?
it re-checks. receipts are pinned to the tree fingerprint they ran on, so if the code moved since the handoff, the old exit codes don't count and it reruns. the part it can't verify is a judgment like "ready to send." those stay a guess until something re-proves them on the…

Tue, Oct 20

That's @JennHull-builds's first reply.