SOTA long memory eval with open source models

Show HN: SOTA long memory eval with open source models

SOTA long memory eval with open source models operates in show hn launch.

Profile

Cursor published a great post last week on scaling long-running autonomous coding agents to build a browser.We’ve been exploring a similar idea, but applied to math proofsWe show how a swarm of agents, coordinated via shared memory, can generate a Lean proof for a non-trivial multi-step math problem-Putnan A2-that a single agent struggled with. We were feeling fancy so we wrote a full post and captured the runtime.Harness will be public soon(tm) for you to run it yourself.

Within the show hn launch space, the company focuses on its core offering rather than a broad product line.

Directory data places it at the Show HN launch stage.

Website: ensue.dev/blog/beating-memory-benchmarks