Loading the edition…
· Past edition · 5 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Research & academia
Describes an eight-stage open post-training recipe and its data, rewards and infrastructure, with reported results against the official base release. The captured v2 abstract is a later revision from 2026-09-25.
Why it matters: Open post-training recipes give others a concrete basis for replication.
Research & academia
Introduces executable unfamiliar-world sandboxes for evaluating whether systems can explore and apply new rules; reported outcomes vary across trajectories. The captured v2 abstract is a later revision from 2026-10-08.
Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.
Why it matters: Unfamiliar executable worlds can test exploration beyond memorized tasks.