encypherai
They flag real students as cheaters, mislabel original writing as “likely AI,” and rely on statistical guesswork that just isn’t reliable. Even OpenAI shut down their own detection tool, citing low accuracy.
So I built EncypherAI: an open-source tool that embeds verifiable cryptographic metadata into AI-generated text at the moment of creation. Think of it like a digital fingerprint: invisible, tamper-proof, and verifiable in milliseconds.
- No changes to how the text looks or reads
- Works with OpenAI, Anthropic, local models, or custom pipelines
- Lightweight Python package with CLI
It uses invisible Unicode variation selectors to embed the metadata without altering the visible text.
Metadata can include model ID, timestamp, purpose, and even user or session IDs, all verifiable offline using HMACs.
We're hoping this becomes a baseline standard for AI content attribution, something platforms and LLM providers can adopt to prove when something was generated, instead of guessing. This is already sparking conversations with leading LLM providers building toward responsible AI infrastructure.
Here's the GitHub: https://github.com/encypherai/encypher-ai
Website: https://encypherai.com?utm_source=hn&utm_medium=post&utm_cam...
Article + 1-min explainer: https://encypherai.com/blog/what-if-ai-content-came-with-bui...
Would love your thoughts. Is this the kind of system we need to make AI content more trustworthy?
A video overview & demo of the python package can be found on our homepage: https://encypherai.com/
Show HN: EncypherAI, Open-source tool for cryptographically verifying AI text
https://github.com/encypherai/encypher-ai
Hi HN, I'm one of the makers of EncypherAI. We built this tool because current AI detection systems often fall short when it comes to reliably identifying AI-generated content. Instead of relying on guesswork, EncypherAI embeds cryptographically verifiable metadata directly into AI-generated text. If the metadata is present, you can confirm with 100% certainty which model produced the text,...
However, the study highlights a potential trap: passively offloading critical thinking tasks to AI could hinder development. For younger generations especially, proactively cultivating strong critical thinking skills is essential to truly harness AI's power. It's about augmenting their abilities, not outsourcing them.
It’s interesting to consider how architectures fundamentally different from autoregression might address this limitation more directly. While autoregressive models are incentivized towards a limited form of planning, they remain inherently constrained by sequential processing. Text diffusion approaches, for example, operate on a different principle, generating text from noise through iterative refinement, which could potentially allow for broader contextual dependencies to be established concurrently rather than sequentially. Are there specific architectural or training challenges you've identified in moving beyond autoregression that are proving particularly difficult to overcome?