Marius Hobbhahn

2 months ago | arxiv.org | Bilal Chughtai |Stefan Heimersheim |Marius Hobbhahn

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

2 months ago | lesswrong.com | Marius Hobbhahn

This is a personal post and does not necessarily reflect the opinion of other members of Apollo Research. Many other people have talked about similar ideas, and I claim neither novelty nor credit. Note that this reflects my median scenario for catastrophe, not my median scenario overall. I think there are plausible alternative scenarios where AI development goes very well.

Nov 18, 2024 | lesswrong.com | Marius Hobbhahn

TLDR: We want to describe a concrete and plausible story for how AI models could become schemers. We aim to base this story on what seems like a plausible continuation of the current paradigm. Future AI models will be asked to solve hard tasks. We expect that solving hard tasks requires some sort of goal-directed, self-guided, outcome-based, online learning procedure, which we call the “science loop”, where the AI makes incremental progress toward its high-level goal.

Nov 16, 2024 | lesswrong.com | Marius Hobbhahn

I want to make a serious effort to create a bigger evals field. I’m very interested in which resources you think would be most helpful. I’m also looking for others to contribute and potentially some funding. Which resources would be most helpful? Suggestions include:Open Problems in Evals list: A long list of open relevant problems & projects in evals.

Nov 11, 2024 | lesswrong.com | Marius Hobbhahn

In our engagements with governments, AI safety institutes, and frontier AI developers, we found the concept of the “evaluation gap” (short: ‘evals gap’) helpful to communicate the current state of the art and what is needed for the field to move towards more robust evaluations. In this post, we briefly explain the concept and its implications. For the purpose of this post, “evals” specifically refer to safety evaluations of frontier models.