MoE Expert Offloading: 125B on a 12GB GPU, With Catches
MoE expert offloading lets a 12GB GPU run a 125B model, but only for one user at a time. What Strata's numbers say, and what I'd run instead.
Read the full story →Latest
Your Agent A/B Test Was Broken Before You Ran It
In parimutuel betting your own bet moves the odds you get, so you can't test a strategy against half your bankroll. Agents have the same problem, and almost nobody running…
Half My Agent’s Budget Goes to Checking Its Own Work
I built the quality gate last, in an afternoon, as the cheap safety rail. Then I added up the API bills by…
I Rewrote the Test Until My Writing Passed It
Five commits in four days, every one adjusting the grader that judges this blog's drafts, every one triggered by a verdict I…
The Bug Was Reproducible. My Logs Weren’t.
A post on this site ended in a raw API payload for 151 days. Fixing it took two minutes. Explaining it took…
Credential Scanners Are Wearing Crawler Costumes
71.9 percent of traffic claiming to be Googlebot was hunting for .env files. Of 13,670 credential probes wearing a named crawler user…
Crawled, Indexed, or Cited: How to Read AI Traffic in Your Server Logs
Training, indexing, and live answering are three different things happening to your site. Here is how to tell them apart — and…