Jake Mendel

The Open Philanthropy has just launched a large new Request for Proposals for technical AI safety research. Here we're sharing a reference guide, created as part of that RFP, which describes what projects we'd like to see across 21 research directions in technical AI safety. This guide provides an opinionated...

Open Philanthropy is launching a big new Request for Proposals for technical AI safety research, with plans to fund roughly $40M in grants over the next 5 months, and available funding for substantially more depending on application quality. Applications (here) start with a simple 300 word expression of interest and...

This is a linkpost for Apollo Research's new interpretability paper: "Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition". We introduce a new method for directly decomposing neural network parameters into mechanistic components. Motivation At Apollo, we've spent a lot of time thinking about how the computations...

Tl;dr: We generalize the mathematical framework for computation in superposition from compressing many boolean logic gates into a neural network, to compressing many small neural networks into a larger neural network. The number of small networks we can fit into the large network depends on the small networks' total parameter...

This part-report / part-proposal describes ongoing research, but I'd like to share early results for feedback. I am especially interested in any comment finding mistakes or trivial explanations for these results. I will work on this proposal with a LASR Labs team over the next 3 months. If you are...

Written at Apollo Research Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain crucial structural information beyond superposition, as seen in circular arrangements of day-of-the-week features and in the rich structures of feature UMAPs. We don’t currently have good concepts for talking...

This is a linkpost for: www.apolloresearch.ai/blog/the-first-year-of-apollo-research About Apollo Research Apollo Research is an evaluation organization focusing on risks from deceptively aligned AI systems. We conduct technical research on AI model evaluations and interpretability and have a small AI governance team. As of 29 May 2024, we are one year old....