T
Oct 28, 2026Three more runs of two AI agents in a box: the test set was the whole story
Runs 5 to 7 of the Claude plus Grok sandbox built a tariff classifier, a sanctions screener and a...
Oct 28, 20261 min read0 reactions1 comments
Tag archive
Runs 5 to 7 of the Claude plus Grok sandbox built a tariff classifier, a sanctions screener and a...
We put Claude and Grok in a locked-down VM four times and changed one thing per run. Two runs built...
Five two-minute failures on October 8 sit in the status page history. Four were HTTP 200s that...
9 experiments across 6 research threads — the honest weekly roundup, losing runs included. Posted...
5 experiments across 5 research threads — the honest weekly roundup, losing runs included. Posted...
xAI published the For You feed's actual ranking weights. Copy-link share = 20.0, a like = 0.5, a...
4 experiments across 4 research threads — the honest weekly roundup, losing runs included. Posted...