Cursor Agents Rebuild SQLite from 835-Page Manual, Cost Varies 15x by Model Mix
StanfordAILab · x · 2026-07-21
A team of agents from Cursor successfully rebuilt SQLite in Rust using only its 835-page manual, without access to a reference executable. \n\nThe replica managed to pass 100% of a held-out test suite. Interestingly, the team noted a 15x variance in cost depending on the mix of models used. This provides a compelling case study for multi-agent effects using recent long-horizon coding benchmarks like ProgramBench.
Related event: Cursor's Multi-Agent System Rebuilds SQLite in Rust, Slashing Costs 15x(8 posts)→
More from coding & agent
- TMLR paper: enforced thinking doesn't reliably make LLM agents disclose key info to users — SharonYixuanLi · 2026-10-27
- Resin lets an agent build standalone LLM inference engines; vLLM and SGLang optimize DeepSeek kernels differently — AccBalanced · 2026-10-27
- How I let my cloud Grok Bot code on my Mac mini via Tailscale, no public ports — talkaboutdesign · 2026-10-27
- Context layout is a cost decision: one memory edit can bust your entire agent prompt cache — dscape · 2026-10-27
- Alchemy adds effect/Workflow support across Durable Objects, Workflows and Lambda Durable Functions — samgoodwin89 · 2026-10-27
- Alchemy's Lambda Web Functions run plain Node web servers on Lambda, no OpenNext needed — samgoodwin89 · 2026-10-27