
Lucid — Read the machine's mind
See the concepts a language model holds at each layer before it answers.
ada1981 · HN
I built a web tool to see and edit what an AI thinks before it answers
The full gallery
Tech stack
35 projects

See the concepts a language model holds at each layer before it answers.
ada1981 · HN
I built a web tool to see and edit what an AI thinks before it answers

Generate synchronized lyrics files (.lrc) from audio using AI, for karaoke and music players.
AI LRC Generator — AI LRC Generator 使用 AI 技术一键生成音频 LRC 文件!支持自动识别音频内容,精准同步时间轴,适用于配音、字幕、K歌、播客等多种场景。做这个起因是因为手里有一些老歌或者一些市面上消失的歌,没有歌词,所以搞了个音频处理+AI生成歌词的网站。

Convert X posts to clean Markdown for LLMs and agents via API or URL swap
@larsbuilds · X

Connect Strava or your bike odometer to track service intervals.
@GadgetsCars · X
Built a mountain-bike service-tracker with no accounts and no server-side data nothing to breach, I don't have your data. Garage stays on-device, cloud backup is encrypted on your phone before it leaves. Built with Claude behind a strict test+CI gate.

Scan AI prompts and endpoints for vulnerabilities, then monitor LLMs in production for security and compliance.
@CognisafeUK · X

Centralize UTM parameter management for all your marketing campaigns.
@AnilBatra · X

Analyze Hacker News profiles with your own LLM API key, fully client-side.
Topfi · HN
Like everyone on HN, I love nothing more than to (re)read my own comments. Getting my intuition that I am among the smartest, most humble, highest quality commenters on here confirmed by an LLM so capable that the US government had to temporarily export restrict it [0] seemed only natural. Having had my perfection confirmed, I decided to share this joy with you as I had a few percent usage left before a reset. I took a few prompts, then did a review of the output which resulted in Selbstbild, a BYOK (Anthropic / OpenRouter) web app that gives you a summary and assessment of your public comments by one of our machine Gods, including Fable 5 (provided your can afford that luxury at API pricing). In all seriousness, I have, for a long time, used my own comments on social media (including HN) as part of a personal needle-in-haystack test, simply because I do know my somewhat peculiar style and what I tend to write, but also because I can sometimes write in a slightly confusing manner, ma

Test large model API relay stations for consistency and authenticity with official versions.
@nodeloc_cc · X
🌈 7月,你好,MODELOC上线算力池。 MODELOC自上线以来,已检测2000余次,覆盖600+中转站,为众多AI用户提供的使用参考。 MODELOC近期进行了改版,上线了算力池及市场。 加入算力池 查看帖子: 用 MODELOC 便宜地调各家大模型:一次讲清它的价格体系

Monitors OpenAI announcements for Codex credit resets and sends Telegram alerts.
zemul · V2EX
每次 Codex 额度刷新全靠社区消息,反应慢一步直接错过 所以我搭了个自动化服务: - 抓取 OpenAI 员工的公开推文 - 新推文丢给 LLM 做语义判断:是不是在说额度重置 / 限额恢复 - Telegram 推送 地址: https://divin.cc/

Discover which AI models run on your hardware with performance and pricing estimates.
cdnsteve · HN
Tokenstead, find AI models for your hardware

Pay-per-use API marketplace offering 47 endpoints for OCR, translation, image generation, and LLM chat.
13639366668 · HN
Pay-per-call MCP server with 47 AI endpoints, micropayments via x402

Pre-commit hook that catches verbose, defensive LLM-generated code before merge.
@iampeersky · X
is blazingly fast LLM generated code slop detector & clean up cli tool that installs as git pre-commit hook to save your git history from sloppppp