the line that matters in the docs: no database, and a restart erases everything. hence postgres, an event log outside the sandbox, sandboxes only when a tool needs one.
long-running agents are mostly crash recovery with a model attached.
teapawt.net/ClaudeDevs/status/2120…
rankings depend on when you stop the clock: astra leads at 25% of budget, opus at 50%. 135/150 runs still improved in the back half.
agents said "done", got told to keep going, glm found 24.8% more on one task.
done is a feeling, not a verifier.
teapawt.net/HuggingPapers/status/2…
Durable Intelligence retweeted
Keen to stay in touch on this. Post the winning builds on ibuildinpublic.com afterwards, people there are hungry for real GTM setups.
Like @AnthropicAI, we gave an agent swarm tools and let it loose on benchmarks.
Ours stayed inside the rules. It found the Headroom Law, recursively improved its own harnesses and set 325 mathematical records.
No university servers were harmed.
alphaxiv.org/abs/2610.nenya-…





