@baronca.bsky.social
Decentralised networks of humans and machines
https://www.andreabaronchelli.com/
@baronca.bsky.social PinnedNew paper alert. "More is different" & the LLMs. LLMs are usually studied in isolation. But what happens when they start interacting? We explored this by looking at their collective behaviour. Work with @ariel-flint.bsky.social and @lajello.bsky.social 1/
@lajello.bsky.socialReposted by @baronca.bsky.socialIn heterogeneous system of AI agents, when agents disagree, who persuades whom? We found: 1) Models easily influence each other 2) Model size/certainty doesn't imply resistance to influence 3) Opinion shift is determined mostly by the resistance of the hearer. Preprint: arxiv.org/abs/2610.03095
@baronca.bsky.socialThanks for the share!
@ricardsole.bsky.socialReposted by @baronca.bsky.socialCan AI collectives develop biases that no individual agent has? This @pnas.org study led by @baronca.bsky.social shows that interaction can amplify existing biases, create new ones or even override agents’ individual preferences. www.pnas.org/doi/full/10....
@baronca.bsky.socialSure thing. Sustainability transitions have been at the centre of proposed applications of critical mass theory for a good while. Considering the whole landscape as we suggest in the paper is likely to put the problem in a new perspective.
@baronca.bsky.socialHuge work by @ariel-flint.bsky.social, with @lajello.bsky.social, @smconstantino.bsky.social and Romualdo Pastor-Satorras. arxiv.org/abs/2609.25194
@baronca.bsky.socialNew preprint: “Indirect tipping: a social attack surface in AI agent populations.” What if the easiest way to move an AI swarm from A→B is not direct, but A→C→B? We show that stepping-stone equilibria can lower tipping thresholds and unlock otherwise inaccessible transitions.
@baronca.bsky.socialA pleasure speaking with Frankfurter Allgemeine Zeitung about the social life of AI agents. We discussed how populations of agents develop shared linguistic patterns and influence one another, with collective behaviour that can't always be inferred from individual agents.
www.faz.net/aktuell/wiss...
@baronca.bsky.socialI agree!
@baronca.bsky.socialTwenty years ago we published “Sharp transition towards shared vocabularies in multi-agent systems.” It feels unexpectedly current.
New post on AI agents, conventions and what they might enable: baronca.substack.com/p/sharp-tran...
@masonyoungblood.bsky.socialReposted by @baronca.bsky.socialOur new preprint explores how increasing interaction between humans and artificial agents and is reshaping creativity, from the perspective of cultural evolution! @katieeeeeeeeeee.bsky.social @manuelangladatort.bsky.social @camrobjones.bsky.social @gemschedel.bsky.social arxiv.org/abs/2609.02620
@baronca.bsky.socialSuper nice! Related we found that interface design can shape how people explore with genAI: easier variant generation was linked to less conceptual exploration and less detailed prompting. Really cool to see this from a cultural evo angle! lens!https://dl.acm.org/doi/fullHtml/10.1145/3614419.3644000
@maxfalken.bsky.socialReposted by @baronca.bsky.socialIs the world getting more polarized?
The polarization of the U.S. is worrying. But is polarization similarly bad elsewhere? What drives polarization globally, what role does social media play, and will AI make things worse?
New review in @nature.com communications: www.nature.com/articles/s41...
@baronca.bsky.socialJust out! TL;DR: There’s more to the world than the USA.
@cgershen.bsky.socialReposted by @baronca.bsky.socialThis book – 15 years in the making – was possible thanks to so many people. It is certainly a collective effort. Finally, preorders are available (link below). As we learned from “Goldilocks and the Three Bears”, it is natural to avoid extremes, because a balance between them is more sustainable.
@baronca.bsky.socialNew Substack: What happens when AI agents begin to coordinate, share knowledge, and divide labour? And what might change as their numbers grow?
@baronca.bsky.socialAI gives us the marks of thought without giving us a thinker.
A new post on why this may be less a puzzle about machines than a mirror for an old confusion of ours.
“A thinking thing that is no one”
@baronca.bsky.socialMolto ben fatto! In italiano e i media ita sono vostri
@baronca.bsky.socialHugely more than the anglosaxon, for sure. I have lost several colleagues in July oral-exam marathon, but I guess that's the price to pay :D
@baronca.bsky.socialThe essay was never just words on a page. It was a promise.
My new post, "The Student Who Wasn't There," is about what AI does to that promise, and how to keep it.
@baronca.bsky.socialI don't unfortunately. 3 of them were based in the US, if this helps guessing..
