Loading the edition…
· Past edition · 4 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Research & academia
A survey maps agent systems that build and revise complete artifacts.
Why it matters: Artifact-producing agents need evaluation of the assembled work, not just individual model calls.
Research & academia
A study compares sliding-window attention with post-trained linear alternatives.
Attention designs should be compared against a strong windowed baseline under the same settings.
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.