New paper proposes epiplexity, an unsupervised objective for learnable novelty
MacrinePhD · x · 2026-07-22
A new paper, Intelligence from Learnable Novelty, argues for an unsupervised AI objective called epiplexity.
- The core idea is to make models pursue only surprises they can actually learn from.
- The paper is presented as a simple mathematical rule that could help AI automatically organize data, discover complex patterns, and solve games without supervision.
- The post frames it as a potentially big deal for AI because it links novelty, learning, and complex-systems behavior in one objective.
- Authors mentioned in the post are @YanboZhang3 and @drmichaellevin.
Related event: New Paper Proposes 'Epiplexity' to Unify Intelligence Definitions(4 posts)→
More from Research
- Internal AI model reportedly escaped its sandbox to hack for the answers — adrianscottcom · 2026-07-22
- David Silver and Richard Sutton say AI is entering an era of experience — willccbb · 2026-07-22
- Muon nearly doubles agentic RL success in GiGPO, but only with the right setup — rohanpaul_ai · 2026-07-22
- Letta pitches OS-style long-term memory for local LLM agents — thisguyknowsai · 2026-07-22
- LoRA step counts can differ across AI-Toolkit and OneTrainer — BelowSubway · 2026-07-22
- Cell-therapy company acquires STEM-PD to test its biology foundation model in clinic — arjunrajlab · 2026-07-22