Tootfinder

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu
https://arxiv.org/abs/2506.00320

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we propose Dyna-Think, a thinking framework that integrates planning with an internal world model with re…

Thanks to your incredible support, we've made it to €4889! 💙 Our goal is €12,439 to continue the fight for justice. Every donation matters in pushing this cause ahead. Thank you for standing with us! 🙏 Find out more and donate here: https://chardonsbleus.org/donate

Francesca Albanese, UN Special Rapporteur on the Occupied Palestinian Territories: ‘Israel commits crimes like it breathes. It must be stopped’ | #ELPAÍS English

""The [newly formed] Debcrafters’ […] team will take the lead on syncing & merging packages from Debian, reviewing proposed migration issues, upstreaming Ubuntu deltas, and take ownership of major transitions […]""
Makes me wonder how many similar efforts Canonical/Ubuntu already announced over the years to improved the interaction with Debian – and what became of them.

WordPress may be run by… that guy, but it still has a massive user base. They all need better accessibility documentation.
@… wants to improve it, but needs sponsors:
https://

The Metaphysics of Protection: Emergence, Agency, and the Ontological Status of Logical Qubits
Kamran Majid
https://arxiv.org/abs/2507.00023 https://

The Metaphysics of Protection: Emergence, Agency, and the Ontological Status of Logical Qubits
This paper argues that the practice of fault-tolerant quantum computation, specifically the mechanism of Quantum Error Correction (QEC), offers a profoundly new lens through which to examine foundational questions of ontology, emergence, and interpretation. We move beyond the standard debate on quantum speedup to ask: What is the nature of the entity--the logical qubit--that is being protected, and what does the active, goal-directed process of its protection reveal about physical reality? We a…

Exciting Update: New Goal Set at €12,439! 💼 With your amazing help, we've already hit €4889. To reach our target, we're counting on you. Your support makes a real difference. Thank you for being part of this journey! 🙏 👉 https://chardonsbleus.org/donate

My friend Marty was like "Hey man, Fran needs help" and you know what, Fran is an awesome dude and a great asset to Milwaukee, and he gave me a chance to show & sell my work last year so I pitch a bit of money towards him.
And then more people did, and more, and it doubled the same day, and doubled again since last night! Smashed the original goal.
Community. We build it. Be there for each other. Help when you can.
➡️

Donate to Help Fran Heal and Cover Living Expenses, organized by Francisco Ramirez
Hello, I'm Francisco, most call me Fran. I'm a printmaker in Milwaukee, … Francisco Ramirez needs your support for Help Fran Heal and Cover Living Expenses

A look at the lack of consensus in the tech industry on what AGI is, whether LLMs are the best path to it, and what AGI might look like if or when it arrives (Melissa Heikkilä/Financial Times)

Why Big Tech cannot agree on artificial general intelligence
It has been tipped as the next big breakthrough out of Silicon Valley, but is it a scientific goal — or a marketing buzzword?

"What's it going to take to win this in the next 15 minutes" asks the pundit on BBC.
Well I'm no highly-paid pundit, but I'd suggest "a goal" is the correct answer there.
#Euro2025

Thanks to you, we’ve raised €4889 ! Our goal: €12,439 to keep pushing this legal battle forward. Thank you for your generosity! 💙 👉 https://chardonsbleus.org/donate

Columbia University trustees removed control of the student disciplinary process from the University Senate,
with the trustees taking control themselves of the process through the provost’s office.
The intent was to make sure that any student guilty of violating university regulations during an anti-genocide protest would be severely punished.
One goal is to make sure that students engaged in such protest are removed from the university and can’t do it again.
Anot…

The Situation at Columbia XVIII
When I first started writing here about what was going on at Columbia, part of the motivation was that I didn’t understand myself a lot of what was happening, especially the actions of the tr…

As long as error messages like this can happen, I refuse consider the possibility that matrix could be a secure messaging solution for the masses. I mean... you can't be serious?
If your goal is average users, your No 1 design principle must be that you never bother users with the details of your technical design, which they don't understand anyway. That's a main reason why PGP failed, and people still don't get it. (I mean... I don't understand what that means, and …

What Exactly Does Guidance Do in Masked Discrete Diffusion Models
He Ye, Rojas Kevin, Tao Molei
https://arxiv.org/abs/2506.10971 https://

What Exactly Does Guidance Do in Masked Discrete Diffusion Models
We study masked discrete diffusion models with classifier-free guidance (CFG). Assuming no score error nor discretization error, we derive an explicit solution to the guided reverse dynamics, so that how guidance influences the sampling behavior can be precisely characterized. When the full data distribution is a mixture over classes and the goal is to sample from a specific class, guidance amplifies class-specific regions while suppresses regions shared with other classes. This effect depends …

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
Michael Amir, Matteo Bettini, Amanda Prorok
https://arxiv.org/abs/2506.09434 https://

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
The success of teams in robotics, nature, and society often depends on the division of labor among diverse specialists; however, a principled explanation for when such diversity surpasses a homogeneous team is still missing. Focusing on multi-agent task allocation problems, our goal is to study this question from the perspective of reward design: what kinds of objectives are best suited for heterogeneous teams? We first consider an instantaneous, non-spatial setting where the global reward is b…

Mike Huckabee, the US ambassador to Israel, has said that the US is no longer pursuing the goal of an independent Palestinian state,
marking what analysts describe as the most explicit abandonment yet of a cornerstone of US Middle Eastdiplomacy.
https://www.

Working with AI: Measuring the Occupational Implications of Generative AI
Kiran Tomlinson, Sonia Jaffe, Will Wang, Scott Counts, Siddharth Suri
https://arxiv.org/abs/2507.07935

Working with AI: Measuring the Occupational Implications of Generative AI
Given the rapid adoption of generative AI and its potential to impact a wide range of tasks, understanding the effects of AI on the economy is one of society's most important questions. In this work, we take a step toward that goal by analyzing the work activities people do with AI, how successfully and broadly those activities are done, and combine that with data on what occupations do those activities. We analyze a dataset of 200k anonymized and privacy-scrubbed conversations between users an…

Exciting Update: New Goal Set at €12,439! 💼 With your amazing help, we've already hit €5134. To reach our target, we're counting on you. Your support makes a real difference. Thank you for being part of this journey! 🙏 👉 https://chardonsbleus.org/donate

Thanks to you, we’ve raised €5134 ! Our goal: €12,439 to keep pushing this legal battle forward. Thank you for your generosity! 💙 👉 https://chardonsbleus.org/donate

Thanks to your incredible support, we've made it to €4889! 💙 Our goal is €12,439 to continue the fight for justice. Every donation matters in pushing this cause ahead. Thank you for standing with us! 🙏 Find out more and donate here: https://chardonsbleus.org/donate

Thanks to your incredible support, we've made it to €4889! 💙 Our goal is €12,439 to continue the fight for justice. Every donation matters in pushing this cause ahead. Thank you for standing with us! 🙏 Find out more and donate here: https://chardonsbleus.org/donate

Exciting Update: New Goal Set at €12,439! 💼 With your amazing help, we've already hit €4889. To reach our target, we're counting on you. Your support makes a real difference. Thank you for being part of this journey! 🙏 👉 https://chardonsbleus.org/donate

Thanks to you, we’ve raised €4889 ! Our goal: €12,439 to keep pushing this legal battle forward. Thank you for your generosity! 💙 👉 https://chardonsbleus.org/donate

Wow! 🌟 We've already raised over €4889 towards our goal of €12,439! Let's keep the momentum going to support justice. Each donation brings us one step closer to achieving our target. Thank you for your amazing support! 💙 Donate now at: https://chardonsbleus.org/donate