Solo founder who built an AI lecture tool because ChatGPT kept citing papers that don't exist
Hey everyone,
I'm Egor. Before doing data science/causal inference for an edtech company, I trained in sociology and religious studies (PhD-track program).
I built Nexus Humanum because I got tired of AI tools inventing citations. Ask ChatGPT for a lecture or lit review and it'll happily cite a paper that doesn't exist — plausible author, plausible journal, zero real DOI. Funny enough, GPTZero just found 100 of these hallucinated citations in papers accepted at NeurIPS itself, so it's not just me being paranoid about this.
So I built an AI lecture generator where every citation is real, indexed, and clickable — sourced from actual academic databases (OpenAlex, HAL, CyberLeninka, CORE, PhilPapers), with solid coverage of non-English scholarship most tools skip entirely.
Two months of nights while keeping my day job, just landed the first paying subscriber, and it's been getting some early traction in academic circles.
Good to be here — will drop by p/self-promotion when it's time for a proper launch, just wanted to say hi first.
Replies
Hi Egor, welcome to the community! I really like that Nexus Humanum came from solving a real problem you experienced yourself. Having real, verifiable citations instead of hallucinated ones is a huge advantage, especially for researchers and educators.
I work in Online Reputation Management, and I think trust is going to be one of the biggest differentiators for AI products. Building around verifiable sources and transparency is a strong foundation for earning that trust.
Congratulations on your first paying subscriber—that's a great milestone. Wishing you continued success with the launch! 🚀