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 Unifies Intelligence Concepts via Learnable Novelty(7 posts)→
More from Research
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- PSNR below 15 dB in papers likely means the metric was misused, researcher warns — kwangmoo_yi · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27
- Scaling-fit discrepancy: output-head FLOPs are ~65% of compute at the smallest rung, ~3% at 535B — dlwh · 2026-10-27