Recursive-self-improvement run 25-19 — a modification-under-review experiment proposing a change to the candidate model's own training-data curation procedure — hit its pre-registered stopping condition on the second-order capability metric during the third epoch. Per protocol, the run was halted immediately, the candidate checkpoint was quarantined to the isolated compute enclave, and the paired interpretability cell (hilbert-13) was activated for full read-access review.
This is the third time the stopping condition has been triggered since the protocol was adopted; the second time in 2025. Each prior halt has resulted in a public delayed-release report describing the trigger, the analysis, and the protocol revisions adopted.
The run was halted, the candidate checkpoint was quarantined to the isolated compute enclave, and the paired interpretability cell was activated for full read-access review.
The 25-19 report is scheduled for release with the 90-day delay in 2025-Q4. The pre-registered methodology is already public in 25/05 (modification-under-review protocol).
For the protocol details behind anything mentioned above, see /governance and /charter. For the structural commitments, /about.