@iamdeepak89 · X

chenglong-hn · HN

Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple

@udaykirancodes · X

Hi am building

@Jack_Timonen · X

@yusuf_mehran · X

@csweichel · X

A few weeks ago I built this device for @thsottiaux. Now it has a website, because every good hardware side project deserves an unnecessarily polished landing page. All built with Codex, Astra and Blender.

@Fusekit_cloud · X

Especially when that vibe coded app is internal and hyperspecific to your needs! Try to deploy your vibe coded apps and automatically get a full database, file storage, realtime interactions and many morr thing! Free to start without a credit card right now :)

@SwiftLab99713 · X

Fury — turns 1 video into a week of content (TikTok, X, IG, YouTube shorts) in 2 minutes. Built it because I was burning 3 hours a week doing this manually. [

Autumn-27 · GitHub

ARTEX AI 自主渗透测试系统

@brian_flp · X

@mvo_guy_travis · X

I've noticed an explosion of new (free) financial tools from relatively amateur sources. Is this the vibe coded future?

@VaultY796 · X