New paper links intelligence to a learnable-novelty view of Epiplexity
theomitsa · x · 2026-07-22
A paper titled Intelligence from Learnable Novelty proposes a closed-form approximation of Epiplexity and argues that it is deeply connected to intelligence.
- The authors say they derived a closed-form approximation of Epiplexity.
- They interpret Epiplexity as a form of learnable novelty.
- The post frames this as a new way to think about what intelligence is, backed by the paper’s theoretical derivation.
Related event: New Paper Proposes Epiplexity to Unify Intelligence Definitions(5 posts)→
More from Research
- US Department of Energy Partners with Arcee AI to Build Open Science Model — huggingface · 2026-07-22
- DOE and Arcee AI launch Genesis-Science-1 as an open-weight research model — _akhaliq · 2026-07-22
- US DOE Partners with Arcee.ai to Build Trillion-Parameter Open Science Model — latkins · 2026-07-22
- Arcee.ai Joins US DOE to Build Trillion-Parameter Open Science Model — latkins · 2026-07-22
- Arcee AI says it has joined DOE’s Genesis Mission to build Genesis-Science-1 — latkins · 2026-07-22
- A 20-part breakdown of what actually powers an AI agent — goyalshaliniuk · 2026-07-22