[2/2] Joining us will be @jennysaffran.bsky.social, from @uwmadison.bsky.social; @noranewcombe.bsky.social, from Temple University; @pyoudeyer.bsky.social, from Inria; and Noam Sigelman, from The Hebrew University of Jerusalem. 📅 June 10-12, 2026 +info ⬇️ www.bcbl.eu/events/stati...

🔍 What happens when you give middle-schoolers unrestricted access to ChatGPT for science tasks? Findings from our new paper led by Rania Abdelghani w/ @koumurayama.bsky.social @celestekidd.bsky.social Hélène Sauzéon 🧵👇

New blog post: The Phylogenetics of Artifacts — inferring the evolution of cultural objects, artificial life forms, and language models. From cat genetics to ancient myths to LLMs. 🧬 1/n

Wow, some of my old #EvolutionOfLanguage #EoL pals may have just done something huge for #AILaw data attribution #LLM #AIGovernance Specifically @pyoudeyer.bsky.social @nicolasyax.bsky.social @stepalminteri.bsky.social Evolutionary biology can track LLM phylogeny! developmentalsystems.org/phylolm

The Phylogenetics of Artifacts - A deep dive into the evolution of cultural objects, artificial life forms and language models

Developmental Systems, a Blog of the Flowers Lab

developmentalsystems.org

Major new system and result from the team: SOAR is an open-source self-improving genAI system pushing the frontier of ARC performances using program synthesis It relies on using LLMs as self-improving smart operators for evolutionary search

Julien Pourcel@jul-p.bsky.social · last yr.

Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!) It brings LLMs from just a few percent on ARC-AGI-1 up to 52% We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code. 🧵

Using LLMs to advance the cognitive science of collectives Very interesting new paper by @sucholutsky.bsky.social Katherine Collins @norijacoby.bsky.social @billdthompson @roberthawkins.bsky.social arxiv.org/pdf/2506.00052

Le travail de Samuel Bianchini à partir des algorithmes de @pyoudeyer.bsky.social mis en lumière par le Jeu de paume dans son expo IA

Humans' ability to invent their own games & goals is at the core of open-ended learning. Understanding and modeling computationally how they do it would be enlightening to understand better human cognition and build open-ended AI Great step in this direction in new paper by Guy Davidson et al.

I reviewed "These Strange New Minds: How AI Learned to Talk and What It Means" by Chris Summerfield. melaniemitchell.me/EssaysConten...

royalsocietypublishing.org/toc/rstb/202...

Cool

Nikita Lisitsa@lisyarus.bsky.social · last yr.

Published my WebGPU Particle Life simulation online! Obviously it requires WebGPU support, and it's quite resource-demanding, so I've set the particle count to 64k for now. Also it probably doesn't work on mobile; will fix later. Enjoy: lisyarus.github.io/webgpu/parti...

Another one.

Here is a cool Flow-Lenia simulation, which is a continuous cellular automaton with two distinct features: 1. Mass conservation - sum of all activations is constant through time 2. Localized update rules - enables simulations with differently behaving matter on the same grid

Very happy that our paper received both the EvoApps best paper and the EvoStar best student paper! Congrats team!! Emergent Kin Selection of Altruistic Feeding via Non-Episodic Neuroevolution arxiv.org/abs/2411.10536

Emergent kin selection of altruistic feeding via non-episodic neuroevolution

Kin selection theory has proven to be a popular and widely accepted account of how altruistic behaviour can evolve under natural selection. Hamilton's rule, first published in 1964, has since been exp...

arxiv.org

Clément Moulin-Frier@clemmoulinfrier.bsky.social · last yr.

Max Taylor-Davies will present our new paper at the Evostar conference on Thursday: Emergent Kin Selection of Altruistic Feeding via Non-Episodic Neuroevolution arxiv.org/abs/2411.10536 A joint work with @hamongautier.bsky.social , Timothé Boulet and myself. A quick summary below:

Check out @nicolasyax.bsky.social thread about our paper (co-supervised by @pyoudeyer.bsky.social) where we show that evolutionary tree reconstruction can be successfully applied to map LLMs to map relations and predict their performance! Currently at @iclr-conf.bsky.social

Nicolas Yax@nicolasyax.bsky.social · last yr.

🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥 In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with @stepalminteri.bsky.social and @pyoudeyer.bsky.social ! Here is a brief recap ⬇️

Generative AI is a cultural transmission technology: it plays a growing role in generation, selection and transmission of ideas/opinions in human society 🧠🔄🌐 And yet we understand very little of this dynamics at this point 🤔❓ A step forward is our #ICLR2025 paper !👇

Gaia Molinaro@gaiamolinaro.bsky.social · last yr.

What's wrong with evaluating #LLMs after a single interaction? Come find out @iclr-conf.bsky.social and learn how cultural attraction theory can help us do better. Poster #288, 10 am.

Imagine you can compute a (very) cheap behavioural signatures for LLMs and from it 1) infer their history (which previous models they derived from) 2) build large maps to navigate spaces of 100s of models 3) predict (coarsely) their performances in benchmarks That's PhyloLM 🚀

Nicolas Yax@nicolasyax.bsky.social · last yr.

🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥 In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with @stepalminteri.bsky.social and @pyoudeyer.bsky.social ! Here is a brief recap ⬇️

We are starting a new major research project investigating the joint development of curiosity and metacognition in adolescents, where the Flowers lab will collaborate with @mjgruber.bsky.social 's lab at Univ. Cardiff, and Yana Fandakova at Univ. Trier !!! Open postdocs positions, see below 👇

Matthias Gruber@mjgruber.bsky.social · last yr.

Interested in curiosity and metacognition in childhood and adolescence? Join us at Cardiff University (UK) for a Postdoc position in an international collaboration with @yanafandakova.bsky.social (Germany) and @pyoudeyer.bsky.social (France). Please repost! #DevPsych #PsychSciSky #neuroskyence

Why Self-Determination Theory Needs Computational Modelling: The Case of Competence and Optimal Challenge by @codingconduct.cc E. Lintunen N. Aly @creativeendvs.bsky.social osf.io/n6x8s/downlo...

Forcing Diffuse Distributions out of Language Models "When LLMs are used for real-world tasks where diversity of outputs is crucial their inability to produce diffuse distributions over valid choices is a major hurdle" New method to address this challenge by Zhang et al.: arxiv.org/pdf/2404.10859

Accepting “the bitter lesson” and embracing the brain’s complexity by Dyer and Richards. Great article! www.thetransmitter.org/neuroai/acce...

"The Appeal of Insight: Why Riddles and Whodunits Captivate Us" - These studies contribute to a growing literature in which the cultural success of fictional stories is explained by their ability to tap into specific cognitive mechanisms. osf.io/preprints/ps...

Extreme stances about AI and LLMs in particular (be them deflationary or inflationary) are very likely wrong, valid and certainly not good for an healthy debate. But where do they come from? We (with @giadapistilli.com) argue that common cognitive biases may play a role: osf.io/preprints/ps...

Dirk Wulff@dirkwulff.bsky.social · last yr.

Do LLMs think? Excited to share our updated preprint critically discussing two "Justaic" stances claiming that LLMs lack cognition because they are "just" next-token predictors or "just" machines. Led by @zakashussain.bsky.social and with @ruimata.bsky.social . osf.io/preprints/os...

Humans excel at estimating their own competence and progress on tasks. But can LLM agents do the same? With 🧭MAGELLAN, our agent predicts its own learning progress across vast goal spaces, even generalizing to new tasks! 📄Paper: arxiv.org/abs/2502.07709

@cartathomas.bsky.social · last yr.

🚀 Introducing 🧭MAGELLAN—our new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.🌍✨Learn more: 🔗 arxiv.org/abs/2502.07709 #OpenEndedLearning #LLM #RL

Enabling forms of metacognition in LLMs is a frontiers challenge in #AI We've made progress in this direction with MAGELLAN 🧭: curiosity-driven LLMs learn to predict and generalize their own learning progress in very large spaces of goals 🚀 This is then used for automatic curriculum learning 👇

@cartathomas.bsky.social · last yr.

🚀 Introducing 🧭MAGELLAN—our new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.🌍✨Learn more: 🔗 arxiv.org/abs/2502.07709 #OpenEndedLearning #LLM #RL

“The days of pretending we have binary, easy-to-recognize categories of machines & living beings are over.” — @drmichaellevin.bsky.social

Living Things Are Not Machines (Also, They Totally Are) | NOEMA

Our formal models of life, computers and materials fail to tell the entire story of their capabilities and limitations.

noemamag.com

From the point of view of science I've never been too excited about the Game of Life. But now I realize that what's really exciting about it is what it tells us about what we can call metaengineering... writings.stephenwolfram.com/2025/03/what...

New research project: Lluminate - an evolutionary algorithm that helps LLMs break free from generating predictable, similar outputs. Combining evolutionary principles with creative thinking strategies can illuminate the space of possibilities. www.joelsimon.net/lluminate

Very good points Thomas Wolf ! This is to address this grand challenge that various labs (and mine in particular) have been working on mechanisms enabling AI systems to have capabilities for curiosity and metacognition 🧵

Thomas Wolf@thomwolf.bsky.social · last yr.

I shared a controversial take the other day at an event and I decided to write it down in a longer format: I’m afraid AI won't give us a "compressed 21st century" Here: thomwolf.io/blog/scienti... It's an extension of this interview discussion from the AI summit: youtu.be/AxBd3G0lFLs?...

This is great news that Andrew Barto and Richard Sutton were awarded the #TuringAward 🚀 Thread 🧵

Quanta Magazine@quantamagazine.org · last yr.

Andrew Barto and Richard Sutton have won the A.M. Turing Award for developing the theoretical foundations of reinforcement learning, a key method behind many major breakthroughs in artificial intelligence. 🧵