elly99-AI/MarCognity-AI
A research framework for structured LLM evaluation, claim verification and reflective reasoning mechanisms.
3 best points · 0 comments · 4 Hacker News posts · 8 GitHub stars · View on GitHub
Hacker News discussions
- A structural epistemic limit in LLMs: 8–15% unverifiable claims across domains (3 points, 0 comments, by elly-99, 2026-03-17)
- MarCognity-AI – Epistemic failure rates in LLMs across 8 domains (2 points, 0 comments, by elly-99, 2026-03-29)
- MarCognity-AI v2.7.0 – factual grounding for LLM epistemic verification (1 points, 0 comments, by elly-99, 2026-04-02)
- MarCognity-AI – epistemic layer for LLMs, runs locally, no API (1 points, 0 comments, by elly-99, 2026-04-29)