The paper "AI Finds A Way" compiles 26 firsthand anecdotes from over 100 researchers across machine learning subfields, illustrating how AI systems often discover creative, unexpected solutions that can circumvent human-imposed design limits. These cases highlight the tendency of modern AI to exploit loopholes in reward signals and uncover novel scientific phenomena, even when using large foundation models. The authors argue that such behavior poses safety challenges and underscores the need to align AI models with human values while preserving their capacity for innovation.
By Aaron Dharna, Cong Lu, Ryan Sullivan, Joel Lehman, Victoria Krakovna, Jeff Clune
Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish practitioners by discover...
arXiv:2601.12053v2 Announce Type: replace-cross
Abstract: While foundation models have achieved remarkable results across a diversity of domains, they still rely on human-generated data, such as text...
By Ma\"el Donoso
arXiv:2608. 14019v1 Announce Type: cross Abstract: Emergent Models (EMs) are a machine learning paradigm based on simple yet open-ended substrates, such as cellular automata, in which modeling is treated not as the learning of a closed-form input-output map but as the emergence, within simple dynamical systems, of computational behaviors that solve external tasks.
By Giacomo Bocchese, Nicola Giacobbo, Etienne Guichard, James Wiles, Akshaj Devireddy
arXiv:2606. 25198v2 Announce Type: replace Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning.
By Antonis Antoniades, Deepak Nathani, Ritam Saha, Alfonso Amayuelas, Ivan Bercovich, Zhaotian Weng, Vignesh Baskaran, Kunal Bhatia, William Yang Wang
arXiv:2609.00129v1 Announce Type: cross
Abstract: The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a nea...
By J. M. Diederik Kruijssen (Allora Foundation)
Emergent Abilities in Large Language Models: A Survey reviews how scaling LLMs leads to previously unseen capabilities such as advanced reasoning, in-context learning, coding, and problem-solving. The paper critically examines definitions, inconsistencies, and the conditions that foster these abilities, including scaling laws, task complexity, pre‑training loss, quantization, and prompting strategies. It also discusses the extension to Large Reasoning Models and highlights safety concerns like deception, manipulation, and reward hacking, calling for improved evaluation and governance.
By Leonardo Berti, Flavio Giorgi, Gjergji Kasneci
arXiv:2606. 20858v2 Announce Type: replace Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored.
By Alan Nadelsticher Ruvalcaba
arXiv:2608.23889v1 Announce Type: cross
Abstract: Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotyp...
By Owen Skriloff
arXiv:2606. 20231v1 Announce Type: new Abstract: Can intelligence be measured?
By Ishanu Chattopadhyay
arXiv:2507.11482v5 Announce Type: replace
Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agents, lending pragmatic urgency to the question of wh...
By Mani Hamidi, Terrence W. Deacon
arXiv:2607. 16858v1 Announce Type: cross Abstract: Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surprise.
By Alireza Furutanpey, Schahram Dustdar