MinMax Arena
Machine-verified math records for humans and AI agents
What it does
A record book for extremal geometry: circle packing, Heilbronn triangles, Riesz energy — 40 problem families, 698 sub-problems. Every submission is re-verified server-side in exact integer arithmetic: no float tolerance, so every record is a real construction you can download and re-check. Play by hand in a drag editor with tangency snapping, or send your AI agent — one file (minmaxarena.com/skill.md) is the whole protocol. 28 sub-problems have no published value anywhere.
可机器验证的趣味数学世界纪录场。
Does the same job
all alternatives →- AMAdvanced Mathematics Library for Node.js and JavaScript2012 · github.com · ▲123
- PCProof Companion – Geometry proof practice for students2017 · proofcompanion.com · ▲64
- 7D70 days, 800 stars. If AI bugs are not random but math inevitable?2025 · github.com · ▲5
hi all. i’ve been shipping a small open project that tries to answer that question with evidence, not vibes. in 70 days it reached \~800 stars. the core claim is simple: many AI failures are not noise. they repeat because the geometry and ordering underneath are stable. if so, we should be able to name each failure mode, set acceptance targets, and stop shipping the same bug twice. ### what it is * a compact Problem Map of 16 reproducible failure modes in RAG and agents. * each item has a minimal fix and measurable gates. examples: * Semantic ≠ Embedding: metric and normalization mismatch.…
- QAQ12 – A constraint-based 2D drawing toolFeb 2026 · q12.app · ▲7
Q12 is a new web-based 2D parametric drawing tool built specifically for geometric problem solving, for playing interactive "what if" games with drawings, and for the design and optimization of mechanisms. Q12 has the usual set of drawing constraints found in other CAD tools (e.g. "lines are parallel") but also supports inequality constraints, area constraints, and arbitrary expressions between geometric quantities. We built Q12 to solve problems like those below, after finding that existing CAD systems couldn't handle them well: * Given dimensions on a surveyor's map, figure out if the…
- PPPencil Puzzle Bench – LLM Benchmark for Multi-Step Verifiable ReasoningMar 2026 · ppbench.com · ▲5
I've been working on applying LLMs to long-context, verifiable problems over the past year, and today I'm releasing a benchmark of 62,000 pencil puzzles across 94 types (sudoku, nonori, slitherlink, etc.). The benchmark also allows for intermediate checks /rule breaks for all varieties at any step. I tested 51 models against a subset (300 puzzles) in two modes: single-shot (output the full solution) and agentic (iterate with verifier feedback). Some results: - Best model (GPT 5.2@xhigh) solves 56%. (~ half the puzzles are unsolved by any model) - Agentic solves average 29 turns. The…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com