Newest First.

Every report the corpus ingests, in the order it landed. Real reports don’t carry a publish date in the source yet, so they sort by entry number until that’s added.

Entry 1
Autonomous Multi-agent Research at Scale

An agent was asked to run a large structured-research build unattended overnight. It produced 2,208 usable records and a complete 9,364-subject deterministic sweep — and wasted, conservatively, more than half of what it spent doing so.

14 failuresRead report →