Published:
Agents can spend test-time compute by trying, observing, and revising. We derive an Elo reference for repeated sampling, then show that in a 2022 two-week coding marathon, current agents plateau within 24 hours while top humans keep improving.
Published:
We integrate FrontierCS into Harbor and release a preview long-horizon agent leaderboard on 178 open-ended algorithmic tasks. Kimi K2.6 and Claude Code Opus 4.7 show similar headline capability, but very different failure modes.
Published:
Agents can spend test-time compute by trying, observing, and revising. We derive an Elo reference for repeated sampling, then show that in a 2022 two-week coding marathon, current agents plateau within 24 hours while top humans keep improving.
Published:
We integrate FrontierCS into Harbor and release a preview long-horizon agent leaderboard on 178 open-ended algorithmic tasks. Kimi K2.6 and Claude Code Opus 4.7 show similar headline capability, but very different failure modes.
Published:
We integrate FrontierCS into Harbor and release a preview long-horizon agent leaderboard on 178 open-ended algorithmic tasks. Kimi K2.6 and Claude Code Opus 4.7 show similar headline capability, but very different failure modes.
Published:
Agents can spend test-time compute by trying, observing, and revising. We derive an Elo reference for repeated sampling, then show that in a 2022 two-week coding marathon, current agents plateau within 24 hours while top humans keep improving.
Published:
我曾无数次向大海呼唤，