Developer Tools1 month ago
CraftScore | AI Engineering Intelligence & Recruitment Platform
Measure engineering craft using Git analytics and code quality metrics.
ricardo_santis2 · Product Hunt
CraftScore Measure engineering craft, not AI output.
The full gallery
Tech stack
22 projects
Measure engineering craft using Git analytics and code quality metrics.
ricardo_santis2 · Product Hunt
CraftScore Measure engineering craft, not AI output.
Score startup ideas based on specificity, evidence quality, and risk clarity using AI.
@nellaiorgs · X
Building NELL Labs -- an AI-native startup validation platform. Instead of generic LLM answers, it scores your idea across specificity, evidence quality, risk clarity, and next-step usefulness, so you know if it's actually validated or just sounds good.
Find competitor SERP weak spots and easy-to-rank long-tail keyword opportunities.
@quorankSERP · X
Compare decisions across four frontier AI models (GPT, DeepSeek, Gemini, Claude) in one workspace with sandboxed code preview.
@painterner · X
After a year away, I’m back to indie hacking. Built with Claude and GPT in two weeks, Disidea is my first launch of the year: four AIs debate your decisions in one thread. Try it: Questions? Ideas? Let’s build great products and make money. Who’s in?
Analyze app reviews to discover underserved SaaS and mobile app niches worth building.
@sflorimm · X
Canvas for inspecting LLM weights tensor-by-tensor with quantization error and distribution analysis.
alesha-pro · GitHub
atlas Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for every weight tensor
Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.
Compare language model performance at solving Redactle puzzles.
pampas · HN
Redactle LLM Leaderboard
Upload a CAS PDF to get AI portfolio analysis with benchmark comparisons and allocation insights.
@iASHeeesh · 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