Tootfinder

Here’s a reason to never use Gumroad.
https://www.fastcompany.com/91330297/doge-sahil-lavignia-gumroad

Thanks to DOGE, Gumroad’s founder has a second job with the VA
The creator economy pioneer Sahil Lavingia on his eyebrow-raising decision to embrace DOGE—and, after thinking it over, open source.

"Ocean currents can generate electricity, and our study shows Africa's seas have some of the strongest"
#Africa #Oceans #Energy

Ocean currents can generate electricity, and our study shows Africa's seas have some of the strongest
The world's oceans cover more than 70% of Earth's surface. They're filled with currents, some much stronger than the fastest flowing large rivers. These currents can be harnessed as clean, marine renewable energy. Marine energy is much more predictable and reliable than many other forms of renewable energy because unlike the sun and wind, which regularly do not produce electricity, ocean currents never stop moving around the planet. New research has found that the eastern and south-eastern coas…

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
Haowei Wang, Rupeng Zhang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang
https://arxiv.org/abs/2506.06151

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on external knowledge makes RAG systems vulnerable to corpus poisoning attacks that manipulate generated outputs via poisoned document injection. Existing poisoning attack strategies typically treat the ret…

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
Jingyu Xiao, Ming Wang, Man Ho Lam, Yuxuan Wan, Junliang Liu, Yintong Huo, Michael R. Lyu
https://arxiv.org/abs/2506.06251

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in automated front-end engineering, e.g., generating UI code from visual designs. However, existing front-end UI code generation benchmarks have the following limitations: (1) While framework-based development becomes predominant in modern front-end programming, current benchmarks fail to incorporate mainstream development frameworks. (2) Existing evaluations focus solely on the UI code generation task, whereas p…

ENMA: Tokenwise Autoregression for Generative Neural PDE Operators
Armand Kassa\"i Koupa\"i, Lise Le Boudec, Louis Serrano, Patrick Gallinari
https://arxiv.org/abs/2506.06158

ENMA: Tokenwise Autoregression for Generative Neural PDE Operators
Solving time-dependent parametric partial differential equations (PDEs) remains a fundamental challenge for neural solvers, particularly when generalizing across a wide range of physical parameters and dynamics. When data is uncertain or incomplete-as is often the case-a natural approach is to turn to generative models. We introduce ENMA, a generative neural operator designed to model spatio-temporal dynamics arising from physical phenomena. ENMA predicts future dynamics in a compressed latent …

Cloudflare open sourced an OAuth library mostly written by Claude, showing how AI handles mechanical implementation while humans guide with context and judgment (Max Mitchell)
https://www.maxemitchell.com/writings/i-read-all-of-cloudflares…

Max Mitchell's Personal Portfolio Website
Max Mitchell's personal portfolio website showcasing his photography, YouTube videos, coding projects, and work history.

The monster isn't in the machine. It's in the mirror
https://brilliantcrank.com/every-generation-discovers-the-same-monster/?ref=brilliantcrank-newsletter
via @…

SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
Xinghang Li, Jingzhe Ding, Chao Peng, Bing Zhao, Xiang Gao, Hongwan Gao, Xinchen Gu
https://arxiv.org/abs/2506.05692

SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code. In this work, we introduce \benchmark, a benchmark specifically designed to assess the security of LLM-generated code. The dataset encompasses a wide range of common software development scenarios and vulnerability types. Building upon this benchmark, we deve…

Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests
Stefan Dascalescu, Adrian Marius Dumitran, Mihai Alexandru Vasiluta
https://arxiv.org/abs/2506.05990

Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests
Competitive programming contests play a crucial role in cultivating computational thinking and algorithmic skills among learners. However, generating comprehensive test cases to effectively assess programming solutions remains resource-intensive and challenging for educators. This paper introduces an innovative NLP-driven method leveraging generative AI (large language models) to automate the creation of high-quality test cases for competitive programming assessments. We extensively evaluated o…

Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework
Tianyi Zhang, Shidong Pan, Zejun Zhang, Zhenchang Xing, Xiaoyu Sun
https://arxiv.org/abs/2506.05623

Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework
Infrastructure-as-Code (IaC) generation holds significant promise for automating cloud infrastructure provisioning. Recent advances in Large Language Models (LLMs) present a promising opportunity to democratize IaC development by generating deployable infrastructure templates from natural language descriptions, but current evaluation focuses on syntactic correctness while ignoring deployability, the fatal measure of IaC template utility. We address this gap through two contributions: (1) IaCGen…