Submissions from github.com/elly99-ai

		MarCognity-AI v2.7.0 – factual grounding for LLM epistemic verification (github.com/elly99-ai)
		1 point by elly-99 13 days ago \| past \| discuss
		MarCognity-AI – Epistemic failure rates in LLMs across 8 domains (github.com/elly99-ai)
		2 points by elly-99 17 days ago \| past
		A structural epistemic limit in LLMs: 8–15% unverifiable claims across domains (github.com/elly99-ai)
		3 points by elly-99 29 days ago \| past