Tootfinder

I believe I have "mild” (relative to others I've heard about) Long COVID and my symptoms include, fatigue, memory loss, loss of focus, loss of motivation, worse sleep.
It's real folks.
https://mastodon.social/@augieray/114841505817793827

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
Harry Mayne, Ryan Othniel Kearns, Yushi Yang, Andrew M. Bean, Eoin Delaney, Chris Russell, Adam Mahdi
https://arxiv.org/abs/2509.09396

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its prediction by modifying the input such that it would have predicted a different outcome. We evaluate whether LLMs can produce SCEs that are valid, achieving the intended outcome, and minimal, modifying the input no more than necessary. When asked to generate…

The contrast between Google AI search results, which are terrible and totally unreliable, and NotebookLM is amazing.
I think it is irresponsible from Google to integrate AI search results in Google Search...
#ai #googlesearch

DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction
Yuliang Zhu, Jing Cheng, Qi Xie, Zhuo-Xu Cui, Qingyong Zhu, Yuanyuan Liu, Xin Liu, Jianfeng Ren, Chengbo Wang, Dong Liang
https://arxiv.org/abs/2506.10309

DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction
Dynamic Magnetic Resonance Imaging (MRI) exhibits transformation symmetries, including spatial rotation symmetry within individual frames and temporal symmetry along the time dimension. Explicit incorporation of these symmetry priors in the reconstruction model can significantly improve image quality, especially under aggressive undersampling scenarios. Recently, Equivariant convolutional neural network (ECNN) has shown great promise in exploiting spatial symmetry priors. However, existing ECNN…

google's algorithm decided to autoplay this after the Reading Rainbow theme song, and I'm really curious why. Not that it's a bad song, but it's definitely not a typical listen for me and completely unrelated to 1980s TV show theme songs..

Tell Congress: NO Funding for Primate Breeding! #AnimalRights

URGENT: Tell Congress NO to Funding Primate Breeding!
Right now, Congress is working on the 2025 federal budget, and the Senate Appropriations Committee has allocated a staggering $30 million to expand primate breeding and research at National Primate Research Centers. This funding will support invasive, unethical experiments on primates—causing unimaginable suffering while advancing unreliable science that fails over 90% of the time in human clinical trials. 🔬 Despite these facts, the NIH asked for $10 million, but the Senate has tripled th…

Fact Check: 2023 Video Could NOT Show A Celebration Of Release Of Israeli Soldiers Detained In 2024 Detention Center Rape Case -- Video Shows An Unrelated Party: https://benborges.xyz/2025/07/10/fact-check-video-could-not.html

"Geht es nach dem deutschen Sozial­wissenschaftler Max Weber, sollte eine Verwaltung auf klaren Zuständigkeiten, regel­basierten Verfahren und Hierarchien aufgebaut sein. Beamte müssten, so Weber, für ihr Handeln rechenschafts­pflichtig sein.
Generative KI-Modelle, die für denselben Input immer wieder neue Resultate liefern, sind das Gegenteil davon. Sie sind nicht verlässlich und ein Albtraum für jede Verwaltung, die auf Logik beruht."
@…

The White House has seized on two unrelated incidents of street crime
as a pretext for a federal government power grab
at a time when violent crime has in fact dropped across the country.
The attempted carjacking of Edward “Big Balls” Coristine in Washington DC
and a street brawl in Cincinnati
are the latest cause célebrè on the American right,
which has long supported Donald Trump’s plans for military and law enforcement crackdowns in largely Democratic c…

Crime is down. But Trump's authoritarian power grabs are escalating.
Random street crimes are being used as pretexts for repression.

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Stanley Ngugi
https://arxiv.org/abs/2508.07075

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Large Language Models (LLMs) struggle with dynamic knowledge updates, especially when new information conflicts with deeply embedded facts. Such conflicting factual edits often lead to two critical issues: resistance to adopting the new fact and severe catastrophic forgetting of unrelated knowledge. This paper introduces and evaluates a novel "unlearn-then-learn" strategy for precise knowledge editing in LLMs, leveraging the parameter-efficient fine-tuning (PEFT) technique, Infused Adapter by I…