Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
A structural epistemic limit in LLMs: 8–15% unverifiable claims across domains
(github.com/elly99-AI)
3 points
elly-99
3 months ago
discuss
2.
▲
MarCognity-AI – Epistemic failure rates in LLMs across 8 domains
(github.com/elly99-AI)
2 points
elly-99
2 months ago
discuss
3.
▲
MarCognity-AI – epistemic layer for LLMs, runs locally, no API
(github.com/elly99-AI)
1 point
elly-99
a month ago
discuss
4.
▲
MarCognity-AI v2.7.0 – factual grounding for LLM epistemic verification
(github.com/elly99-AI)
1 point
elly-99
2 months ago
discuss