HN Showcase
Back to browse
Autonomous Prover Running > 1hr

Autonomous Prover Running > 1hr

by bneb-dev·Mar 17, 2026·4 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●●GemWizardryRabbit HoleBold Bet

Public live feed of an autonomous Lean 4 proof attempt on Ramsey numbers.

Strengths
  • •Transforms opaque research process into public spectator event via live telemetry.
  • •Neuro-symbolic pipeline combines Gemini, Z3, and Lean 4 for robust verification.
  • •Z3 exact finisher filters invalid candidates before expensive Lean kernel verification.
Weaknesses
  • •High barrier to entry; requires understanding of formal logic and Ramsey numbers.
  • •Engine code availability unclear; relies on external Gemini API for formulation.
Category
AI/ML
Target Audience

AI researchers, Mathematicians, Formal verification engineers

Similar To

LeanDojo · AlphaProof · Tactician

Post Description

Hi, I am building an autonomous proof engine that is chasing its second result. Via GitHub gist, you can follow it live.

Similar Projects

Developer Tools●●Solid

Assign tasks to 7 AI agents with -mentions, autonomous mode, OpenClaw

Mysti makes multi-model coding workflows tangible: you can inline-route tasks with @-mentions and have agents execute a pipeline where each one gets the previous output, plus auto-retries for failures. The OpenClaw daemon, WebSocket streaming, status-bar provider switching, and autonomous/semi-autonomous modes show this is more than a toy — it aims to make cross-model review and debate a practical part of your edit loop. The real test will be subscription/config friction and whether multi-agent noise actually improves real-world code quality, but the feature set is a smart, ambitious bet.

Big BrainSlick
bahaAbunojaim
123mo ago