if you are applying to PhD programs in CS, this is for you! specifically, we've seen lots of opportunities tailored towards applicants from underrepresented groups, so several grad students at @browncs compiled a list that we hope is generally helpful cs.brown.edu/degrees/doctora… 1/6

What is intelligence for? In a rare collaboration between top universities and 3 frontier labs, we all agree that alignment should move beyond pathologizing to a positive focus on flourishing. We need north stars not just barbed wire. A close historical analogue comes from psychology. For much of the twentieth century, mainstream psychological science organized its aims around diagnosing, predicting, and treating dysfunction: depression, anxiety, psychosis, addiction, and other forms of impairment. That focus was justified and socially urgent, and it produced progress. Yet the field also discovered a systematic limitation. The constructs and instruments that reliably detect pathology do not, by default, specify what counts as a life well-lived. The turn toward positive psychology expanded the scientific target space by developing distinct theories, taxonomies, and measures for wellbeing, strengths, virtue, purpose, wisdom, meaning, and prosocial functioning, alongside interventions to boost these capacities beyond the status quo. As AI becomes embedded all over society and everyday sensemaking, a solely negative posture risks optimizing our information ecology for risk avoidance rather than human development. It may reduce catastrophic errors but leave agents in a local optimum of superficial and `soulless' assistance, where subtle misalignments abound. It also reveals that alignment is not a purely technical problem. We have to cut across vast disciplines because questions about the good life demand insights from philosophy, pychology, neuroscience, economics, and beyond. We need to work together to build AI systems that explicitly understand, model, and enhance human, animal, and ecological flourishing. The core challenge is therefore to build systems that can represent and reason about wellbeing as a structured manifold of human goods, trade-offs, and temporal dynamics, while enabling individuals and communities to retain agency over what counts as better in their context. While some may explicitly desire a system that is strictly and indiscriminately instruction-following, others must have the genuine option to choose systems configured to support their long-term growth or specific ethical commitments. This distinguishes *consented guidance*, where a user authorizes a system to help align their immediate actions with their higher-order goals, from *technocratic imposition*, ensuring that the pursuit of flourishing remains an exercise of, rather than an infringement upon, human agency. It gives me optimism that we found common ground on such a profoundly complex issue as the end game(s) of AI. Because when learning become cheap, we need to take a serious look at what intelligence is actually for.

If anyone builds it, everyone thrives. Over the past decade, a lot of important work on AI alignment has focused on avoiding harm. But freedom from harm isn't the same as freedom to flourish. In this paper, we introduce 'Positive Alignment'. A positively aligned agent is one that helps us navigate our own value trade-offs, builds our resilience, and acts as a scaffold for human flourishing. Doing this without slipping into top-down, technocratic paternalism is the great design challenge of our time. We think a lot more research is now needed to explore this frontier: how do we align models that actively help us thrive? Amazing work by @RubenLaukkonen, @drmichaellevin, @weballergy, @verena_rieser, @AdamCElwood, @996roma, @FranklinMatija, @shamilch, @_fernando_rosas, @scychan_brains, @matybohacek, @sudoraohacker, and others. arxiv.org/abs/2605.10310

📜 💡**New paper & dataset** Our paper [to be presented as a spotlight at NeurIPS’25] presents DIVE, a novel dataset for aligning GenAI models to pluralistic viewpoints. DIVE and accompanying experiments advocate for a shift in both: alignment strategies and safety evaluations.

What does your favorite language model know about the real world? 🌎 Can it distinguish between possible and impossible events? We find that LM representations not only encode these distinctions, but that they predict human judgments of event plausibility!

🤔🤖Most AI systems assume there’s just one right answer—but many tasks have reasonable disagreement. How can we better model human variation? 🌍✨ We propose modeling at the individual-level using open-ended, textual value profiles! 🗣️📝 arxiv.org/abs/2503.15484 (1/?)

I’m really sad that my dear friend @FelixHill84 is no longer with us. He had many friends and colleagues all over the world - to try to ensure we reach them, his family have asked to share this webpage for the celebration of his life: pp.events/felix

Catch me at the Berkeley Simons Institute today at 3PM PT for a talk on pluralistic alignment! simons.berkeley.edu/workshop…

!!! apply to get to do some of the most fascinating work in the field

Also, next I'll be in London 🇬🇧 for my @GoogleDeepMind internship working on pluralistic alignment with the amazing @verena_rieser @bakkermichiel @996roma @mhtessler and others 🥳 Reach out if you'll be in the area!

How does the human brain represent semantic information from different languages? Our new preprint suggests that bilingual language comprehension relies on shared semantic representations that are systematically modulated by each language! 1/n

applications now open! big focus on language research that is safety/society-centered 🌎

Catch the last event of the @EscuelaPLNmex @naaclmeeting a panel on getting into NLP: insights from experts and peers. Organized by @devoidikk and @dirazuhf panelists: @lexicutioner Emilio Villa Cueva, Roma Patel, Horacio Jarquin and Selene Baez

How well can we understand an LLM by interpreting its representations? What can we learn by comparing brain and model representations? Our new paper highlights intriguing biases in learned feature representations that make interpreting them more challenging! 1/

come talk to us at this *excellent* workshop on cognitive science and language models!