Posts

AI safety research and technical writing

On evals May 1, 2024 Understanding mixture-of-depths Apr 5, 2024 What sorts of systems can be deceptive? Oct 31, 2022 Why you might expect homogeneous takeoff: evidence from ML research Jul 17, 2022 Inductive bias of neural networks on 1D regression: an empirical examination Jun 1, 2022 Non-factorised identifiable variational autoencoders for causal discovery and out-of-distribution generalisation Mar 1, 2022 Are graph neural networks (GNNs) fundamentally bottlenecked? Feb 15, 2022 Sharpness-aware minimisation and label noise Feb 1, 2022 Comparing GPT-3 and RNNs as probabilistic generative models Jan 1, 2022 Investigating short-term climate forecasts with surrogate modelling Dec 20, 2021 Intelligent game playing with AI Jun 1, 2018
https://inwaves.io/posts/feed.xml