Reading this type of papers, I understand (or acknowledge) that I don't understand anything
arxiv.org/abs/2604.04782

People are usually easier to bear with, idk. Wish I could talk.

Doing anything not with human but with LLMs (for example, writing a paper) causes (at least, for me) a some sort of panic attack because I need to trust to all their derivations and conclusions, which may be just hallucinations. It even more deepens my self-doubt about what I am doing. Gross, ngl.

Really excited to present our recent work at #ICLR2026 this week! 🚨

We discover highly coordinated joint behaviours and integrate them into the skill sets of MARL agents, accelerating the search for effective joint strategies in downstream tasks. 🧵👇

Paper link: raulsteleac.github.io/iaro

But wait, there's more! Our call for papers is now LIVE at: openreview.net/group?id=rl-...

We're looking for work on sample efficiency, world models, foundation model agents, multi-agent systems, reward learning, and more: all through the lens of video games. Deadline May 20! #RL #GameAI

Dr. Luke Marris loves LP solvers, maybe MIP will do as well.

Why Open Source? A Game-Theoretic Analysis of the AI Race In recent years, with the advancement of frontier AI, we have observed certain dynamics in open-sourcing and closed-sourcing decisions. We propose a game-theoretic model to analyze these dynamics in t...

Cool morning paper drop: arxiv.org/abs/2604.16227
Why Open Source?

CC: @sharky6000.bsky.social

this is my list +

Digital Ecosystems: Interactive Multi-Agent Neural Cellular Automata

pub.sakana.ai/digital-ecos...

hashtag wisdom

From Togelius et al.

Did I make that or did I prompt [intend] to make?

One Trillion Parameters and No Plans | AI and Games Conference 2025 YouTube video by AI and Games Conference

I gave a talk at AI & Games conf reflecting on whether planners (GOAP, HTN) still have relevance in a world of Gen AI. I see opportunity for neurosymbolic approaches to AI for games that combine symbolic planning with neural language models. Fun live demo at the end.
www.youtube.com/watch?v=N_84...

Hillel Bar-Gera, Stephen D. Boyles, Liron Ravner
Departure Time Choice with Parametric Heterogeneity: Equilibrium and Instability
https://arxiv.org/abs/2604.13831

Hillel Bar-Gera, Stephen D. Boyles, Liron Ravner
Departure Time Choice with Parametric Heterogeneity: Equilibrium and Instability
https://arxiv.org/abs/2604.13831

maybe the best we could've gotten frfr

100 bucks for a bus ticket geez

Imagine what would it mean not to hate yourself!

2026 Call for Papers Workshop on Insights from Negative Results in NLP

📢 The workshop on Insights from negative results will be back at EMNLP'26!

Your most-insightful failures can be submitted in 4 pages by June 25. It's also possible to commit short papers reviewed through ARR.

insights-workshop.github.io/2026/cfp

WW

sorry i am not interested in seeing your political views in my feed

correction: Αληθώς Ανέστη

wait

are you an orthodox cristian?

cool

воистину, воскресе – indeed

btw this fact took me TWO years to understand!

I'd save because I enjoy reading good discussions when they happen (which is rare)

awesome!

Really like some of the Google's Paradigms of Intelligence team papers. They write about sophisticated things, but write quite well

nice pants btw

idk you know that people have wanted that for years on twitter and only super-mega-premium accounts got it as a result

i think you can make cheap editing on bsky because it's decentralised but these days typos and stuff serve as a proof of human not AI creativity xd