The Better AIngels of our Future
Satinder Singh Google DeepMind & University of Michigan
There is no such thing as reward-hacking, there is only bad reward design and good reward design. Indeed, Reinforcement Learning is the solution to alignment, not the problem. I will make the case that what we need are powerful AIs that have their own (human-designed) reward functions that care about long-term consequences of behaviors including instruction-following. I will also briefly lay out a possible research program for building these better AIngels of our future from our frontier models. This program will advance (1) designing good rewards that reflect the better angels of our own nature and (2) planning with local-world models—models that include us.
*From joint position paper with Richard Lewis, University of Michigan
Creative AI Session 3
To score or not to score
Scoring the performance of a machine learning model is a key choice we all make, whether it is the loss for training a model, a gap for understanding alignment, or a metric such as accuracy for predictive performance. This talk considers the score we use in adaptive experimental design for scientific discovery, where we use bandit type approaches to choose experiments. I show some recent theoretical and practical work on adaptive design and discuss the needs of cross disciplinary collaboration for AI in science, for example to empirically validate bandit designs in a genomics lab.
On the other side, machine learning researchers may be tempted to generalise the idea of optimising a score to other aspects of work and life. I argue that it is problematic to convert the diversity of human experience into a single scalar score, and then optimising that score. Finally I discuss some preliminary results on what could be in between scoring and not scoring.
Creative AI Session 4
Science Communication Training Session 2
Effective Science Communication: Crafting an Elevator Pitch for Your Research
Whether explaining your work to collaborators, pitching for funding, talking to the media or interviewing for a top job, clarity will make your work stand out. This hands-on session will give you the tools to translate complex ideas into a clear and concise story. You will walk away with a tailored elevator pitch ready for any occasion.
This session will provide you with:
Exercises to find your core message and focus on what matters most for different audiences. Key concepts to make complex ideas memorable and persuasive. Storytelling techniques to turn complex data into engaging narratives. Individualized advice on public speaking to make the most out of every opportunity.
The Human Context of AI: Whose Perspective Counts?
In Silico, In Vitro, In Vivo: The Protein Design Social
Multimodal AI Studio: Create Your Virtual Idol
Finding Your Path in AI Safety & Security Research
| NeurIPS uses cookies for essential functions only. We do not sell your personal information. Our Privacy Policy » |