Human-aligned AI
Summer School

Speakers | Program | Organizers

The fourth Human-aligned AI Summer School was held in Prague from 17^th to 20^th July 2024. We have met for four intensive days of talks, workshops, and discussions covering latest trends in AI alignment research and broader framings of AI alignment research.

Format of the school

The school is focused on teaching and exploring approaches and frameworks, less on presentation of the latest research results. The content of the school is mostly technical – it is assumed the attendees understand current ML approaches and some of the underlying theoretical frameworks.

The intended audience of the school are researchers interested in learning more about the AI alignment topics, PhD students, researchers working in ML/AI outside academia, and talented students. It is recommended that the participants have a basic general understanding of the AI alignment problem, although the school does not assume deep knowledge of the topics.

This year, the school will cover these main topics:

• Overview of the alignment problem and current approaches.
• Alignment of large language models: RLHF, DPO and beyond. Methods used to align current large language models and their shortcomings.
• Evaluating and measuring AI systems: How to understand and oversee current AI systems on the behavioral level.
• Interpretability and the science of deep learning: What's going on inside of the models?
• AI alignment theory: While 'prosaic' approaches to alignment focus on current systems, theory aims for deeper understanding and better generalizability.
• Alignment in the context of complex systems and multi-agent settings: What should the AI be aligned to? In most realistic settings, we can expect there are multiple stakeholders and many interacting AI systems; any solutions to alignment problem need to solve multi-agent settings.

The school consists of lectures and topical series, focused smaller-group workshops and discussions, expert panels, and opportunities for networking, project brainstorming and informal discussions.
A detailed program will be announced shortly before the event. See below for a program outline and e.g. the program of the previous school for an illustration of the program content and structure.

Speakers

• Ratip Emin Berker – Carnegie Mellon University
• Stephen Casper – Algorithmic Alignment Group, MIT.
• Stanislav Fort – Google DeepMind.
• Jesse Hoogland – Timaeus.
• David Krueger – Centre for the Study of Existential Risk, University of Cambridge.
• Jan Kulveit – Alignment of Complex Systems, Charles University.
• Neel Nanda – Google DeepMind.
• Mary Phuong – Google DeepMind.
• Deger Turan – AI Objectives Institute and Metaculus.
• Vikrant Varma – Google DeepMind.

We are in the process of confirming additional speakers and will update the list over time.

Program of the school

A detailed program is available in the school Swapcard. Any major updates are also announced on the event Discord. The overall schedule is as follows:

Tuesday, July 16

18:00

Informal pre-school welcome social

Wednesday, July 17 – Friday, July 19

9:00	Venue opens for breakfast
9:30 — 18:00	Conference program at the Faculty of Nuclear Sciences and Physical Engineering in Prague Old Town, Břehová 78/7, Praha 1
~18:30	Evening conference events

Saturday, July 20

9:00	Venue opens for breakfast
9:30 — 17:00	Conference program at the Faculty of Nuclear Sciences and Physical Engineering in Prague Old Town, Břehová 78/7, Praha 1

Catered lunch, coffee breaks, and light breakfast are provided during the conference days.

Sunday, July 21

The morning after the school is reserved for informal discussions, project brainstorming, coworking etc. We will provide and recommend some locations for this, and help with coordination. For people continuing to ICML, there are direct train connections from Prague to Vienna taking approximately 4 hours and running several times a day.

Proposing workshop sessions

The school will have several smaller-group workshop sessions, consisting of presenting new topics, interactive activities, and discussion on narrower or technical topics, offered by both invited speakers and selected participants of the school.

If you are interested in presenting a workshop, please send us a brief description of the workshop content (about half a page) along with the intended format and target audience, noting your expertise within the area. Note that the expectation is not to necessarily present your own work, but rather to provide content and activities that enrich the school for other participants. If we think your workshop is a good fit we will get back to you and discuss the content of the workshop in more detail and help you refine it for the school.

Organizers

Program: Jan Kulveit, Tomáš Gavenčiak, and Daniel Filan
Operations: Viktorie Havlíčková
Organized by Alignment of Complex Systems research and Center for Theoretical Study, Charles University, Prague

📧 Contact us at haaiss@acsresearch.org