Compute trends across three eras of machine learning J Sevilla, L Heim, A Ho, T Besiroglu, M Hobbhahn, P Villalobos 2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022 | 202 | 2022 |
Will we run out of data? an analysis of the limits of scaling datasets in machine learning P Villalobos, J Sevilla, L Heim, T Besiroglu, M Hobbhahn, A Ho arXiv preprint arXiv:2211.04325, 2022 | 79 | 2022 |
Machine learning model sizes and the parameter gap P Villalobos, J Sevilla, T Besiroglu, L Heim, A Ho, M Hobbhahn arXiv preprint arXiv:2207.02852, 2022 | 35 | 2022 |
Fast predictive uncertainty for classification with bayesian deep networks M Hobbhahn, A Kristiadi, P Hennig Uncertainty in Artificial Intelligence, 822-832, 2022 | 20 | 2022 |
Parameter, compute and data trends in machine learning J Sevilla, P Villalobos, JF Cerón, M Burtell, L Heim, AB Nanjajjar, A Ho, ... 2022-05-30]. https://docs. google. com/spreadsheets/d/1AAIebj …, 2021 | 15 | 2021 |
Estimating training compute of deep learning models J Sevilla, L Heim, M Hobbhahn, T Besiroglu, A Ho, P Villalobos Epoch, January 20, 2022 | 13 | 2022 |
Investigating causal understanding in LLMs M Hobbhahn, T Lieberum, D Seiler NeurIPS ML Safety Workshop, 2022 | 9 | 2022 |
Trends in GPU price-performance M Hobbhahn, T Besiroglu EPOCH. June 27, 2022 | 9 | 2022 |
Technical report: Large language models can strategically deceive their users when put under pressure J Scheurer, M Balesni, M Hobbhahn arXiv preprint arXiv:2311.07590, 2023 | 8 | 2023 |
Compute trends across three eras of machine learning. arXiv J Sevilla, L Heim, A Ho, T Besiroglu, M Hobbhahn, P Villalobos arXiv preprint arXiv:2202.05924, 2022 | 7 | 2022 |
Compute Trends Across Three Eras of Machine Learning.(2022) J Sevilla, L Heim, A Ho, T Besiroglu, M Hobbhahn, P Villalobos URL: https://arxiv. org/abs/2202.05924. doi 10, 2022 | 5 | 2022 |
Black-Box Access is Insufficient for Rigorous AI Audits S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ... arXiv preprint arXiv:2401.14446, 2024 | 4 | 2024 |
A Causal Framework for AI Regulation and Auditing L Sharkey, CN Ghuidhir, D Braun, J Scheurer, M Balesni, L Bushnaq, ... Preprints, 2024 | 1 | 2024 |
Laplace Matching for fast Approximate Inference in Generalized Linear Models M Hobbhahn, P Hennig ArXiv 2105, 2021 | 1 | 2021 |
Reflection Mechanisms as an Alignment Target: A Survey M Hobbhahn, E Landgrebe, E Barnes NeurIPS ML Safety Workshop, 2022 | | 2022 |
Laplace Matching for fast Approximate Inference in Latent Gaussian Models M Hobbhahn, P Hennig arXiv preprint arXiv:2105.03109, 2021 | | 2021 |
Sequence Classification using Ensembles of Recurrent Generative Expert Modules. M Hobbhahn, MV Butz, S Fabi, S Otte ESANN, 333-338, 2020 | | 2020 |
Large Language Models can Strategically Deceive their Users when Put Under Pressure J Scheurer, M Balesni, M Hobbhahn ICLR 2024 Workshop on Large Language Model (LLM) Agents, 0 | | |