← Latest products

Cerno

CAPTCHA that targets LLM reasoning, not human biology. Open-source TypeScript SDK for human verification. Maze interaction with motor-control analysis, 12 behavioral features scored server-side against per-maze baselines. No ML inference, no third-party calls.

Visit cerno.shexternal site

Reactions (1)

Similar products

by description similarity

  1. GoalChain for goal-orientated LLM conversation flows

    Hacker News19 pts

  2. PG has posted about improving social networks using something like an "intellectual CAPTCHA" many times [1][2][3][4] - "Make users pass a test on basic concepts like the distinction between necessary and sufficient conditions before they can tweet." I felt the same way.

    Hacker News29 pts

  3. Jevgpt

    news.ycombinator.com

    reinventing the wheel with another wheel

    Hacker News26 pts

  4. The 𝗣𝗼𝘄𝗲𝗿𝗳𝘂𝗹 Conversational AI JavaScript Library 💬 — UI for any LLM, supporting LangChain / HuggingFace / Vercel AI, and more 🧡 React, Next.js, and plain JavaScript ⭐️

    Hacker News24 pts

  5. Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

    Hacker News158 pts