Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI code
To my knowledge, this is the first formally verified implementation of a 3D constructive solid geometry (CSG) operation: mesh intersection, implemented in Lean 4 and verified against a concise specification that pins down the surface of the resulting mesh exactly and guarantees practical well-formedness conditions on the triangulation. This project is also an experiment in avoiding having to trust AI-generated code. A human reviewer only needs to read 93 lines of formal specification and run the Lean checker to certify the correctness of the kernel, skipping the intricate 1000+ lines of…
In plain words
This is a formally verified implementation of 3D mesh intersection using Lean 4, designed to eliminate the need to trust AI-generated code. Reviewers need only examine a 93-line specification and run the Lean checker to verify correctness, while the system's 1000+ lines of implementation and 60,000+ lines of proofs are automatically generated and guaranteed correct at compile time. It serves developers and researchers who require cryptographically assured correctness in computational geometry operations.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
To my knowledge, this is the first formally verified implementation of a 3D constructive solid geometry (CSG) operation: mesh intersection, implemented in Lean 4 and verified against a concise specification that pins down the surface of the resulting mesh exactly and guarantees practical well-formedness conditions on the triangulation. This project is also an experiment in avoiding having to trust AI-generated code. A human reviewer only needs to read 93 lines of formal specification and run the Lean checker to certify the correctness of the kernel, skipping the intricate 1000+ lines of AI-written implementation. To prove correctness, AI autonomously wrote over 60,000 lines of Lean proofs, which also never have to be inspected by a human. The Lean checker guarantees conformance to the specification at compile time, with zero trust placed in any LLM. This allows us to treat the implementation and proofs as a black box. I guided the agent through the milestones described in the readme to arrive at the result presented here. Also take a look at the web demo https://schildep.github.io/verified-3d-mesh-intersection/, which runs the verified mesh intersection kernel compiled to WebAssembly in your browser.
Does the same job
all alternatives →- FVFormally verified polygon intersection – Opus 4.8 oneshots, prev failedJun 2026 · github.com · ▲93
To my knowledge, this is the first formally verified implementation of an intersection algorithm for polygons. The experience of working with AI agents on this project changed a lot with recent model releases, as I describe in the readme. Opus 4.8 is able to provide algorithm implementation with formal proof in one shot, whereas previous models required me to provide proof strategies in multiple steps. Trust in the correctness comes entirely from the Lean checker and human review of a small specification, not from the LLM. Also check out the web demo built around the verified core linked in…
- FGForge – Guardrails take an 8B model from 53% to 99% on agentic tasksMay 2026 · github.com · ▲687
Hi HN, I'm Antoine Zambelli, AI Director at Texas Instruments. I built Forge, an open-source reliability layer for self-hosted LLM tool-calling. What it does: - Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware - Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it - Ships with an eval harness and interactive dashboard so you can reproduce every number I wanted to run a handful of always-on agentic systems…
- 3M3D Meshes of Signed Distance Functions in Python2021 · github.com · ▲157
- AAAn algorithm for smoothly filling holes in 3D meshes2018 · erkaman.github.io · ▲104
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 · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
