Turbo Learn — 从文档、图片、拼音文件生成笔记的 AI 学习工具网站

@SpalaAi · X

AI Codereview for Gitlab — 基于大模型(DeepSeek,OpenAI等)的 GitLab 自动代码审查工具；支持钉钉/企业微信/飞书推送消息和生成日报；支持Docker部署；可视化 Dashboard - [查看仓库](https://github.com/sunmh207/AI-Codereview-Gitlab)

@sergey_science · X

Building Gene Inspector - AI platform that helps health practitioners to get more insights from DNA to deliver personalized care.

Aldasams · HN

Show HN: DocFlow – AI documentation updates for GitHub pull requests

hackitup7 · HN

TLDR built a Chrome site blocker that lets you into distracting sites only after you do some math or simple coding (JS only right now). Direct link to extension (the site just gives you more context): https://chromewebstore.google.com/detail/sphinx-earn-your-di... Philosophically it's a speed bump rather than a hard gate, because you'll eventually tear a gate down but you'll leave a speed bump. I've always eventually removed site blockers, or just had them become a nuisance that I reflexively dismiss before getting to distracting sites. Site blockers don't really reduce the "start navigating to a distracting site" muscle memory, and they eventually just become annoying. Dopamine is a hell of a drug. At the same time, I've been getting frustrated that my intermediate/advanced math skills have atrophied, and becoming more senior in my career (plus AI...) has caused my coding skills to atrophy even further. Realistically I'm not going to force myself to do math or coding exercises aft

@hazemnassr · X

@RulianLLP · X

Mine is - it's a "I vibe coded my app, now what?" production checklist, scanner and and active/dead man monitor to make sure you've covered all the small things that could easily break your production environment. My laravel cloud url is -

@fujidevv02 · X

the world's first context-aware, local AI browser pet companion!

niklio · HN

You write 8 text completions and open models score how predictable each word was too them. Predictable => clanker. You can share results with your friends. The scoring checks every word you write against the model's logprobs. Right now I'm using Llama3.1, Deepseek v3 and Qwen3 to keep costs low. I tried to calibrate it so other models (chatgpt/claude) score 100% and interesting human responses score in the 10-30% range. Totally free, no signup

@serkanglatt · X

Developing — 24 proven stock screeners sift through thousands of US tickers to surface just the few worth your time. Unusual stock options activity, options flow & options-backed signals let you see where institutional money is flowing.

@essoratwin · X

Essora - Your personal AI memory. AI knows the world. Essora knows you. Save notes, reminders, ideas, and knowledge in one place. Chat with everything you've saved, create AI twins, and share only the knowledge you choose while keeping the rest private.