Tootfinder

Nearly five months into Trump’s new reign of error,
his administration’s mistakes are multiplying.
https://www.washingtonpost.com/opinions/2025/06/06/trump-mistakes-noem-rfk/

They are not good at this
Nearly five months into Trump’s new reign of error, his administration’s mistakes are multiplying.

But, please. Downsize FEMA and NOAA not the Pentagon.
https://www.theguardian.com/us-news/live/2025/jul/05/texas-flooding-latest-news-updates-guadalupe-river-flood-camp-mystic

Now lets guess what colour ouf the skin this Deputy US Marshal has.
Immigration agents mistakenly detain deputy U.S. marshal in Tucson
#ICE
https://tucson.com/news/local/bo…

Immigration agents mistakenly detain deputy U.S. marshal in Tucson, feds confirm
A deputy U.S. marshal was mistakenly detained by immigration agents inside the federal building that houses Tucson's immigration court, U.S. Marshals Service officials confirmed on Thursday.

I built a solar #meshtastic node
Now, I need to find a place to put it

Unfortunately & conversely, this (below) is the same framing tech bros (and parts of the population) are finding so attractive to anthropomorphize LLMs: These are not machines, and them making mistakes is normal and expected... At the same time, the other card being played (by politics, military & law enforcement) is that AI-driven insights and decision making are _already_ considered superior, infallible and unchallengeable... in the middle of this two pronged rhetoric is the fate o…

The #MCTS BRT looks *PACKED*.

Naar aanleiding van Wired artikel naar deze interessante technologie gekeken, altijd fascinerend dit soort "end-of-days" toepassingen. Belangrijk bij echt grote rampen.
#meshtastic

MeshNet - Meshtastic Nederland
Meshtastic is een off-grid open mesh netwerk dat bruikbaar is tijdens rampen en noodsituaties wanneer gewone communicatie niet meer functioneert...

This https://arxiv.org/abs/2506.02965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this appro…

This https://arxiv.org/abs/2506.02308 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the numb…

This https://arxiv.org/abs/2506.01016 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimistic critics can empower small actors
Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, sm…