Watch 14-Byte AI "brains" attempt to solve a 2D maze (Its hard)

In plain words

This project demonstrates tiny neural networks trained to navigate 2D mazes using only local sensory input. The creator built 14-byte AI models across 46 experimental phases, achieving a 96.5% solve rate on unseen mazes without access to map data or external memory. The project is designed for those interested in neural networks and AI fundamentals, showing how extremely compact models can learn navigation tasks and where they typically fail, such as getting caught in loops.

written from the facts on this page · September 2026

From the sources

In the maker’s words, at launch

Hey HackerNews, I built this project over the last few weeks as a palette cleanser from a failed game launch. I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate. Well - I couldn't, but I got pretty close. 14 Bytes total…

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robotsAug 2026 · cactuscompute.com · ▲537

  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…

• 
  100 Vibe Coding2025 · 100vibecoding.com · ▲351

  Hi HN, I have been making side projects since I was 14, and my team mate (this is his very first side project! Congrats!) designed and implemented the UI. Over time, people kept asking me how they could start coding and turn ideas into reality. So we had an idea. Coding is changing. With AI, the bottleneck is no longer writing every line by hand but knowing how to prompt effectively to reach a working outcome. Our objective is not to make people code better, or even learn to be a proficient software engineer, but just to keep it simple and start building. We want to remove fear and barriers…

• 
  I built a game to help you learn neural network architectures2024 · graphgame.sabrina.dev · ▲321
• 
  Second Brain for AIMay 2026 · github.com · ▲286

  Persistent memory for Claude, ChatGPT & Cursor. Free.

• 
  Second Brain2025 · second-brain-lac-ten.vercel.app · ▲281

  Hi HN, I'm Dom, a solo founder. I built Second Brain to solve a common issue I had with AI chats: the knowledge disappears. There’s no structure, no memory, and no way to reuse or build on them. So I built a tool that combines AI chat with a visual, interconnected knowledge system. Key features: - Save AI responses into editable docs (Notion-style Pages). - AI Visual board with multiple content & chat nodes (like Miro meets ChatGPT). - Add and chat with YouTubes, TikToks, Audio, PDFs, GitHub repos, Looms, websites, etc. - Organize using Projects and Smart Tags — then chat with full contexts.…

• 
  A competition for small neural networks that play strategy gamesSep 2026 · tinybrains.dev · ▲116

  A ranked ladder for small neural networks that play strategy games. Train a model, write an adapter, upload two files, and get measured into a weight class from 8 KiB up.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 19d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• IR
  I replaced a $120k bowling center system with $1,600 in ESP32s▲2,935

  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

• 
  Elevators▲1,680

  How elevators push your buttons

  Life & fun · Jul 2026 · john.fun

• 
  18 Words▲1,160

  Play 18 Words, the free daily word puzzle. The official home is 18words.com. Tap Play now to open today

  Life & fun · Jul 2026 · 18words.com

• BA
  Bento - An entire PowerPoint in one HTML file (edit+view+data+collab)▲1,033

  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

• 
  Getting GLM 5.2 running on my slow computer▲937

  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

• 
  OpenSEO▲928

  Hello! For the last 2 months, I've been building OpenSEO. It's a user friendly UI wrapping the DataForSEO API which has high quality SEO data for keywords, backlinks, AI SEO and competitor research. Instead of paying $100+ per month, you buy DataForSEO credits and pay only for usage. The coolest thing about the project so far has been hearing about what people are building on top of it. People are using coding agents to quickly integrate with Google Search Console, Google Ads and building their own AI SEO and reporting features. Many were already building their own custom solutions around…

  Dev tools · Jul 2026 · openseo.so