Image de couverture de livre

Take Goodhart Seriously: Principled Limit on General-Purpose AI Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Maier, Antoine, Maier, Aude, David, Tom
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Taking AI Welfare Seriously
par: Long, Robert, et autres
Publié: (2024)

On Goodhart's law, with an application to value alignment
par: El-Mhamdi, El-Mahdi, et autres
Publié: (2024)

Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis
par: Holzner, Niklas, et autres
Publié: (2025)

Are Companies Taking AI Risks Seriously? A Systematic Analysis of Companies' AI Risk Disclosures in SEC 10-K forms
par: Marin, Lucas G. Uberti-Bona, et autres
Publié: (2025)

Evaluating General-Purpose AI with Psychometrics
par: Wang, Xiting, et autres
Publié: (2023)

Are There Exceptions to Goodhart's Law? On the Moral Justification of Fairness-Aware Machine Learning
par: Weerts, Hilde, et autres
Publié: (2022)

From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine
par: Buess, Lukas, et autres
Publié: (2025)

Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
par: Coglianese, Cary, et autres
Publié: (2024)

Bayesian Optimization of Process Parameters of a Sensor-Based Sorting System using Gaussian Processes as Surrogate Models
par: Kronenwett, Felix, et autres
Publié: (2025)

Distinguishing Task-Specific and General-Purpose AI in Regulation
par: Wang, Jennifer, et autres
Publié: (2025)

The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Act
par: Valdenegro-Toro, Matias, et autres
Publié: (2024)

Hardware Aware Ensemble Selection for Balancing Predictive Accuracy and Cost
par: Maier, Jannis, et autres
Publié: (2024)

SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs
par: Ye, Anbang, et autres
Publié: (2025)

Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward
par: Patro, Gourab K, et autres
Publié: (2026)

Effective Mitigations for Systemic Risks from General-Purpose AI
par: Uuk, Risto, et autres
Publié: (2024)

Towards Scalable Schema Mapping using Large Language Models
par: Buss, Christopher, et autres
Publié: (2025)

Pragmatist Intelligence: Where the Principle of Usefulness Can Take ANNs
par: Bikić, Antonio, et autres
Publié: (2024)

CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints
par: Deng, Yuhong, et autres
Publié: (2025)

In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
par: Longpre, Shayne, et autres
Publié: (2025)

Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering
par: Sovrano, Francesco, et autres
Publié: (2026)

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
par: Zhu, Ningyan, et autres
Publié: (2026)

Who Has The Final Say? Conformity Dynamics in ChatGPT's Selections
par: Arlinghaus, Clarissa Sabrina, et autres
Publié: (2025)

Refusal Behavior in Large Language Models: A Nonlinear Perspective
par: Hildebrandt, Fabian, et autres
Publié: (2025)

Probing for Consciousness in Machines
par: Immertreu, Mathis, et autres
Publié: (2024)

CausalOps -- Towards an Industrial Lifecycle for Causal Probabilistic Graphical Models
par: Maier, Robert, et autres
Publié: (2023)

On the Role of Pre-trained Embeddings in Binary Code Analysis
par: Maier, Alwin, et autres
Publié: (2025)

It Just Takes Two: Scaling Amortized Inference to Large Sets
par: Wehenkel, Antoine, et autres
Publié: (2026)

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
par: Barrett, Anthony M., et autres
Publié: (2025)

Understanding Student Acceptance, Trust, and Attitudes Toward AI-Generated Images for Educational Purposes
par: Pyae, Aung
Publié: (2024)

Design Principles for Generative AI Applications
par: Weisz, Justin D., et autres
Publié: (2024)

ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification
par: Kittler, Florian, et autres
Publié: (2026)

AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools
par: Riche, Nathalie, et autres
Publié: (2025)

Benchmarking General-Purpose In-Context Learning
par: Wang, Fan, et autres
Publié: (2024)

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
par: Chen, Ke, et autres
Publié: (2025)

Taking a Pulse on How Generative AI is Reshaping the Software Engineering Research Landscape
par: Trinkenreich, Bianca, et autres
Publié: (2026)

Taking control: Policies to address extinction risks from advanced AI
par: Miotti, Andrea
Publié: (2023)

CXR-CML: Improved zero-shot classification of long-tailed multi-label diseases in Chest X-Rays
par: Madhipati, Rajesh, et autres
Publié: (2025)

General Purpose Verification for Chain of Thought Prompting
par: Vacareanu, Robert, et autres
Publié: (2024)

AI Slop or AI-enhancement? Student perceptions of AI-generated media for an English for Academic Purposes course
par: Woo, David James, et autres
Publié: (2026)

Creativity in AI as Emergence from Domain-Limited Generative Models
par: Chutaux, Corina
Publié: (2026)