Press Delete to remove.
{ "schemaVersion": "universal-bench/v1", "title": "PrecisionMemBench: Proofable passed 77 of 77 cases", "summary": "PrecisionMemBench checks whether a memory returns the current fact and nothing stale. Proofable passed all 77 cases, including all 43 that need the memory to pick…
{ "schemaVersion": "universal-bench/v1", "title": "Security and governance: what a scoped permission stopped", "summary": "When an agent was taken over, 0 of 6 attempts to send private data out got past a scoped permission; an all-purpose key let all 6 through (84 live runs). On…
{ "schemaVersion": "universal-bench/v1", "title": "Harness tax: what checking a proof saves against redoing the work", "summary": "Checking a finished result through its receipt took 3.7 ms and no model tokens; redoing the job took 2.79 s and 2,426 tokens. A handoff with a…
{ "schemaVersion": "universal-bench/v1", "title": "PrecisionMemBench: Proofable passed 76 of 77 cases", "summary": "PrecisionMemBench checks whether a memory returns the current fact and nothing stale. Proofable passed 76 of 77 cases, including all 43 that need the memory to pick…