Skip to main content

Posts

Showing posts from January, 2026

New best story on Hacker News: Show HN: isometric.nyc – giant isometric pixel art map of NYC

Show HN: isometric.nyc – giant isometric pixel art map of NYC 513 by cannoneyed | 138 comments on Hacker News. Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: https://ift.tt/tJmXPe5
Post a Comment
Read more

New best story on Hacker News: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete 447 by williamzeng0 | 88 comments on Hacker News. Hey HN, we trained and open-sourced a 1.5B model that predicts your next edits, similar to Cursor. You can download the weights here ( https://ift.tt/glLXfPH ) or try it in our JetBrains plugin ( https://ift.tt/x2sDjyY... ). Next-edit autocomplete differs from standard autocomplete by using your recent edits as context when predicting completions. The model is small enough to run locally while outperforming models 4x its size on both speed and accuracy. We tested against Mercury (Inception), Zeta (Zed), and Instinct (Continue) across five benchmarks: next-edit above/below cursor, tab-to-jump for distant changes, standard FIM, and noisiness. We found exact-match accuracy correlates best with real usability because code is fairly precise and the solution space is small. Prompt format turned out to matter more than we expected. We ran a genetic algorithm over 30+ diff fo...
Post a Comment
Read more

New best story on Hacker News: Show HN: ChartGPU – WebGPU-powered charting library (1M points at 60fps)

Show HN: ChartGPU – WebGPU-powered charting library (1M points at 60fps) 448 by huntergemmer | 139 comments on Hacker News. Creator here. I built ChartGPU because I kept hitting the same wall: charting libraries that claim to be "fast" but choke past 100K data points. The core insight: Canvas2D is fundamentally CPU-bound. Even WebGL chart libraries still do most computation on the CPU. So I moved everything to the GPU via WebGPU: - LTTB downsampling runs as a compute shader - Hit-testing for tooltips/hover is GPU-accelerated - Rendering uses instanced draws (one draw call per series) The result: 1M points at 60fps with smooth zoom/pan. Live demo: https://chartgpu.github.io/ChartGPU/examples/million-points/ Currently supports line, area, bar, scatter, pie, and candlestick charts. MIT licensed, available on npm: `npm install chartgpu` Happy to answer questions about WebGPU internals or architecture decisions.
Post a Comment
Read more

New best story on Hacker News: Show HN: I used Claude Code to discover connections between 100 books

Show HN: I used Claude Code to discover connections between 100 books 428 by pmaze | 131 comments on Hacker News. I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration in comparison. One of my favourite trail of excerpts goes from Jobs’ reality distortion field to Theranos’ fake demos, to Thiel on startup cults, to Hoffer on mass movement charlatans ( https://ift.tt/Kk06zVv ). A fun tendency is that Claude kept getting distracted by topics of s...
Post a Comment
Read more

New best story on Hacker News: Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc.

Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc. 360 by Xyra | 126 comments on Hacker News. Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safely run on my machine, to answer your most nuanced questions. There's also an Alerts functionality, where you can just ask Claude to submit a SQL query as an alert, and you'll be emailed when the ultra nuanced criteria is met (and the output changes). Like I want to know when somebody posts about "estrogen" in a psychoactive context, or enough biology metaphors when talking about building infrastructure. Currently have embedded: posts: 1.4M / 4.6M comments: 15.6M / 38M That's with Voyage-3.5-lite. And you can do amazing compositional vector search, ...
Post a Comment
Read more