Tootfinder

WordPress showed off Telex, its experimental AI development tool, at WordCamp US; CEO Matt Mullenweg called it "V0 or Lovable, but specifically for WordPress" (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/09/02/wordpress-show…

WordPress shows off Telex, its experimental AI development tool | TechCrunch
WordPress CEO Matt Mullenweg introduced the new WordPress AI tool, called Telex, at the company's WordCamp US 2025 conference in Portland last week, alongside other AI experiments.

Neu im DNBLab: Tool zur SRU-Schnittstellenabfrage
#DNBlab

I'm surprised that many people just seem to realize that the golden cage by #Apple is actually a golden cage! 🤷
What have you thought when you decided for that (overpriced) #lockin situation?
Of course, an #iOS

❗ Weitere Informationen – nicht nur zum Thema Diebstahl, sondern auch zu einer Vielzahl anderer Risiken – findet ihr im SiLK-Tool: https://www.silk-tool.de/de. Hier gibt es einführende Informationen, Fragebögen und eine Wissensdatenbank, die gemeinsam das Bewusstsein für Fragen des Schutzes und der Erha…

So viel zum Thema #Chatkontrolle und „Wer nichts zu verbergen hat…“
Wenn die Falschen an der Macht sind und die Strukturen bestehen, wird es übel.
https://www.

ICE to Buy Tool that Tracks Locations of Hundreds of Millions of Phones Every Day
Documents show that ICE has gone back on its decision to not use location data remotely harvested from peoples' phones. The database is updated every day with billions of pieces of location data.

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
Thierry Blankenstein, Jialin Yu, Zixuan Li, Vassilis Plachouras, Sunando Sengupta, Philip Torr, Yarin Gal, Alasdair Paren, Adel Bibi
https://arxiv.org/abs/2510.00307

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
Agents backed by large language models (LLMs) often rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raises a critical point concerning fairness: if selection is systematically biased, it can degrade user experience and distort competition by privileging some providers over others. We introduce a benchmark of diverse tool categories, each containing multiple functionally equivalent tools, to evaluate tool-selection bias. Using t…

Apple dropped ICEBlock, a widely used tracking tool, from its App Store Thursday
after the Department of Justice, at the direction of Attorney General Pam Bondi,
asked Apple to take down ICEBlock, the tool, which allows users to anonymously report ICE agents' presence w
https://www.

Apple takes down ICE tracking apps after pressure from Bondi DOJ
Apple dropped an ICE tracking app from its online store on Thursday in response to the Department of Justice raising concerns that the app put law enforcement officers’ safety at risk.

It's been a crazy week, so don't leave for the weekend until you check out today's Metacurity for the crucial cyber developments you should know, including
--Oracle confirms customer extortion emails, urges patch updates,
--Red Hat confirms security incident and begins remediation,
--Apple drops ICEBlock ICE tracking tool under pressure from DOJ,
--Japan to run out of Asahi beer after cyberattack,
--Air Force probes possible SharePoint breach,
-…

Oracle confirms customer extortion emails, urges patch updates
Red Hat confirms security incident and begins remediation, Apple drops ICEBlock ICE tracking tool under pressure from DOJ, Japan to run out of Asahi beer after cyberattack, Air Force probes possible SharePoint breach, Israeli medical center targeted in suspected Iran attack on Yom Kippur, much more

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
Siddhant Arora, Haidar Khan, Kai Sun, Xin Luna Dong, Sajal Choudhary, Seungwhan Moon, Xinyuan Zhang, Adithya Sagar, Surya Teja Appini, Kaushik Patnaik, Sanat Sharma, Shinji Watanabe, Anuj Kumar, Ahmed Aly, Yue Liu, Florian Metze, Zhaojiang Lin
https://arxiv.…

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-…

Incredible that #google makes it impossible to smoothly delete all your photos, either making you scroll select for hours or forcing you to use 3rd party tools like https://github.com/mrishab/google-phot

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan, Anurag Roy, Ashish Sunil Agrawal, Radha Poovendran, Rameswar Panda
https://arxiv.org/abs/2510.01179

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack of high quality permissively licensed tool-agentic training data. Existing datasets are often limited in diversity, realism, and complexity, particularly regarding multi-tool and multi-turn interactions. To address this gap, we introduce Toucan, the largest publicly available tool-agentic dataset to date, containing …

TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling
Seungheon Doh, Keunwoo Choi, Juhan Nam
https://arxiv.org/abs/2510.01698 https://a…

TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling
While the recent developments in large language models (LLMs) have successfully enabled generative recommenders with natural language interactions, their recommendation behavior is limited, leaving other simpler yet crucial components such as metadata or attribute filtering underutilized in the system. We propose an LLM-based music recommendation system with tool calling to serve as a unified retrieval-reranking pipeline. Our system positions an LLM as an end-to-end recommendation system that i…

Quantum Brush: A quantum computing-based tool for digital painting
Jo\~ao S. Ferreira, Arianna Crippa, Astryd Park, Daniel Bultrini, Pierre Fromholz, Roman Lipski, Karl Jansen, James R. Wootton
https://arxiv.org/abs/2509.01442

Quantum Brush: A quantum computing-based tool for digital painting
We present Quantum Brush, an open-source digital painting tool that harnesses quantum computing to generate novel artistic expressions. The tool includes four different brushes that translate strokes into unique quantum algorithms, each highlighting a different way in which quantum effects can produce novel aesthetics. Each brush is designed to be compatible with the current noisy intermediate-scale quantum (NISQ) devices, as demonstrated by executing them on IQM's Sirius device.

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Janet Jackson:
🎵 If (Kaytranada Remix)
#JanetJackson
https://deyan.bandcamp.com/track/janet-jackson-if-de-yan-tool
https://open.spotify.com/track/0t414ewhjcIiuPVF3QECz2

Maybe AI Was Never a Tool
They can deliver conclusions that feel complete but skip the struggle that gives thought its humanity. This is what I call anti-intelligence—not stupidity, but perhaps better expressed as a kind of counterfeit cognition. It's intelligence without friction that results in output—built in that shared cognitive dynamic—that looks like insight but has bypassed the work that makes insight truly yours.

Maybe AI Was Never a Tool
Using artificial intelligence "responsibly" assumes it is just another tool—it isn't.

Cybercriminals are trying to extort executives with data allegedly stolen through Oracle tool https://therecord.media/possible-clop-campaign-extortion-executives-stolen-data

Tool-Assisted Conformance Checking to Reference Process Models
Bernhard Rumpe, Max Stachon, Sebastian St\"uber, Valdes Voufo
https://arxiv.org/abs/2508.00738 https://

Tool-Assisted Conformance Checking to Reference Process Models
Reference models convey best practices and standards. The reference frameworks necessitate conformance checks to ensure adherence to established guidelines and principles, which is crucial for maintaining quality and consistency in various processes. This paper explores automated conformance checks for concrete process models against reference models using causal dependency analysis of tasks and events. Existing notions of conformance checking for process models focus on verifying process execu…

Thinking about how best to stream a conference..
https://www.tldraw.com/p/tIXG8uAqCKIvFphpFQjTv?d=v1456.-696.2927.1552.page

Perplexity launches a free AI-powered patent research tool in beta to let users search for patents using natural language queries (Emma Roth/The Verge)
https://www.theverge.com/news/811340/perplexity-ai-patent-research-tool

Perplexity’s new AI tool aims to simplify patent research
Perplexity is launching an AI-powered patent research tool that allows you to search for patents using natural language.

A description of the radio astronomy data processing tool DDF Pipeline
Mathis Certenais, Fran\c{c}ois Bodin, Laurent Morin
https://arxiv.org/abs/2509.03075 https://

A description of the radio astronomy data processing tool DDF Pipeline
This paper presents the DDF Pipeline, a radio astronomy data processing tool initially designed for the LOw-Frequency ARray (LO- FAR) radio-telescope and a candidate for processing data from the Square Kilometre Array (SKA). This work describes the DDF Pipeline software and presents a coarse-grain profiling execution to characterize its performance.

LegiScout: A Visual Tool for Understanding Complex Legislation
Aadarsh Rajiv, Klaus Mueller
https://arxiv.org/abs/2510.01195 https://arxiv.org/pdf/2510.011…

LegiScout: A Visual Tool for Understanding Complex Legislation
Modern legislative frameworks, such as the Affordable Care Act (ACA), often involve complex webs of agencies, mandates, and interdependencies. Government issued charts attempt to depict these structures but are typically static, dense, and difficult to interpret - even for experts. We introduce LegiScout, an interactive visualization system that transforms static policy diagrams into dynamic, force-directed graphs, enhancing comprehension while preserving essential relationships. By integrating…

DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems
Rohan Kadekodi, Zhan Jin, Keisuke Kamahori, Yile Gu, Sean Khatiri, Noah H. Bayindirli, Sergey Gorbunov, Baris Kasikci
https://arxiv.org/abs/2510.00229

DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems
The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs consistently underperform compared to frontier models in tool calling scenarios, struggling with both tool selection from large tool sets and accurate argument generation for complex parameter structures. We introduce a methodology that disaggregates a tool-calling t…

mist: MIST protein interaction database (2020)
The Molecular Interaction Search Tool (MIST) is a comprehensive resource of molecular interactions, assembled from severla primary sources. MIST currently supports several species, including:.
This network has 3705 nodes and 15167 edges.
Tags: Biological, Protein interactions, Unweighted

»Cyberrisiko KI-Coding - Angriffsfläche steigt durch unsicheren Code«
Dies ist weder überraschend so wie vorhersehbar. Nur weil ein Tool im allgemeinen beliebt und populär ist, ist es wirklich nützlich oder gar sicher. Ich gehe mal davon aus, dass dies gewisse Firmen sogar in den Bankrott treibt.
🤖

Cyberrisiko KI-Coding - Angriffsfläche steigt durch unsicheren Code
Checkmarx hat die Ergebnisse des jährlichen Reports „Future of Application Security in the Era of AI“ veröffentlicht. Die Studie zeichnet ein umfassendes

Draugnet is a lightweight, open-source tool for anonymous cyber threat reporting. Built for the MISP ecosystem, it lets users submit and track reports — no accounts, no logins, just a simple token. Supports plain text, MISP JSON, and object templates. ideal for CSIRTs, ISACs, and trusted communities. 🔐 Built for anonymity 🧩 Easy MISP integration .
version 1.2.0 released with RTIR, Flowintel and Ollama integration.
Source code:

Two more blog posts on the #Tricycle project over the last few days: firstly, I have found a CAD tool that works for me:
https://www.journeyman.cc/blog/posts-output/20…

Great one-man effort (in his spare time) by my former colleague Maarten Staats! He went where no organisation went before ;)
Still quite tough to find the information underneath - crossing language and other barriers - but by far the best overview of Europe's grid capacity issues there is.
Rightfully getting a lot of traction!

I couldn't believe this didn't exist yet. So I built it myself.   Electricity grid capacity is an issue throughout the whole EU, but there issn't a clear overview. If you wanted to get this insight… | Maarten Staats | 247 comments
I couldn't believe this didn't exist yet. So I built it myself.   Electricity grid capacity is an issue throughout the whole EU, but there issn't a clear overview. If you wanted to get this insight, you would need to find all maps and paint a mental picture from each country's overview maps.   So that's exactly what I did. I built an overview of grid capacity maps for the whole EU. And made it into an interactive tool.   I'm not going to lie. It took more time than I want to admit. But it wa…

I am watching D's and others try to get records (such as Epstein materials) out of the gov't. And the tool they are often using is FOIA (5 USC 552).
Why-the-F are they not also using the Privacy Act (5 USC 552a)?!!! (That little 'a' at the end matters.)
Every person has the right under the Privacy Act (PA) to demand the release of records containing personally identifiable information about them. PA has far fewer exemptions/excuses than FOIA, much tighter time …

from my link log —
VBARE / versioned BARE: A simple alternative to Protobuf & Cap'n Proto for schema evolution.
https://www.rivet.dev/blog/2025-09-24-vbare-simple-schema-evolution-with-maximum-performance
saved 2025-…

VBARE: A simple alternative to Protobuf & Cap'n Proto for schema evolution
At Rivet, we're building an open-source alternative to Cloudflare Durable Objects — a tool for running stateful compute workloads. VBARE is a small but crucial component in meeting the demanding performance requirements of Rivet Actors.

ICE to Buy Tool that Tracks Locations of Hundreds of Millions of Phones Every Day (Joseph Cox/404 Media)
https://www.404media.co/ice-to-buy-tool-that-tracks-locations-of-hundreds-of-millions-of-phones-every-day/
http://www.memeorandum.com/250930/p163#a250930p163

Doc: Amazon's Q Business AI assistant struggled with accuracy and data processing in its first year, drawing complaints; Amazon says the document is outdated (Eugene Kim/Business Insider)
https://www.businessinsider.com/amazon-q-significan…

Amazon internal review found its AI tool Q fell 'significantly' behind rivals on accuracy in its first year
Amazon's AI productivity tool Q Business faced significant accuracy challenges in its first year, leading to customer complaints and service updates.

First keynote at #DocEng25 by Debora Weber-Wulff @… on “Detecting and Documenting Plagiarism and GenAI Use.”
Her main message just on the first slide

> personally, I was interested in cognitive science, partly because I was like, “all this linguistic stuff has no application. It’s pure science. It won’t be turned into a tool against the working class or into a weapon or something.” And then this stuff happens. And I’m like, well, fuck, that was a miscalculation from my part.
from (substack) www.bloodinthemachine.com/p/ai-is-an-attack-from-above-on-wages

Apache Flink is uniquely positioned to serve as the backbone for AI agents, equipping them with the powerful new tool of stream processing. At Berlin Buzzword 2025, Steffen Hoellinger discussed how Flink jobs can be transformed into “Agents”—autonomous, goal-driven entities that dynamically interact with data streams, trigger actions, and adapt their behaviour based on real-time insights.
Watch the full session: #bbuzz returns on 7-9 June 2026: https://tickets.plainschwarz.com/bbuzz26/c/8Hvk0ZvJA/

Großes Update für Canva, Affinity wird kostenlos
Das Grafik-Tool Canva bekommt mehr KI, besseren Video-Schnitt, Marketing-Werkzeuge, Mail-Designer und Formulare – zudem trägt die Affinity-Übernahme Früchte.
https://www.…

Apple-Music-Marketing: Radio bei TuneIn, Tool für den Spotify-Export
Der iPhone-Hersteller ist beim Musikstreaming nach wie vor hinter Spotify platziert. Zwei neue Maßnahmen sollen Kunden weglocken.
http…

"Let us return to 2000: a few days before Joel Spolsky published his Test, Mark Lucovsky gave a talk titled “Windows: A Software-Engineering Odyssey” at the 4th USENIX Windows System Symposium in Seattle, Washington. He was a member of the original Windows NT team from 1988 to the mid-2000s. The PowerPoint slides of the talk are still available online, and I seriously recommend you take a look at them.
Because part of the “odyssey” was, you guessed it, source control."
…

Twenty Years Is Nothing
In a previous edition of this magazine, we argued that English was so pervasive in our industry, nobody even questioned its use anymore. The same can be said of Git. It is difficult to imagine that merely twenty years ago, the landscape of source control tools was more diverse, and the choice of one such tool was much more complicated than today. Actually, Git was not even on the map yet. Before debating whether the hegemony of Git is good or bad, let us go back in time for a little while.

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
Jing-Jing Li, Jianfeng He, Chao Shang, Devang Kulshreshtha, Xun Xian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi
https://arxiv.org/abs/2509.25624

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining (STAC), a novel multi-turn attack framework that exploits agent tool use. STAC chains together tool calls that each appear harmless in isolation but, when combined, collectively enable harmful operations that only become apparent at the final execution step. We apply our frame…

😎 Virtual reality shows promise in easing stress for cardiac patients
#vr

Virtual reality shows promise in easing stress for cardiac patients
Living with cardiovascular disease often takes a serious emotional toll—and with stress known to worsen heart health, there's growing interest in low-risk, innovative ways to help patients cope. New research from UCLA Health suggests that virtual reality (VR) may offer a promising tool to ease psychological stress and support heart health.

I thought I was going to be in luck, as there's a convenient 'Export Data' which generates a .zip containing all the source account data.
Went to the new instance expecting to import that zip, only to be greeted with 'This only supports CSV files'...
FML
SO, my current thought process is to let the new server pull in posts from the original server organically, (with help from

GitHub - nanos/FediFetcher: FediFetcher is a tool for Mastodon that automatically fetches missing replies and posts from other fediverse instances, and adds them to your own Mastodon instance.
FediFetcher is a tool for Mastodon that automatically fetches missing replies and posts from other fediverse instances, and adds them to your own Mastodon instance. - nanos/FediFetcher

Series C, Episode 01 - Aftermath
DAYNA: Avon! [The Sarran attacks, Avon fights and knocks him down, then picks up Orac]
DAYNA: You fight well.
AVON: Only when I have to. [She draws the bow on the downed Sarran] What are you doing?
https://blake.torpidity.net/m/301/108 B7B6

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Yaxin Du, Yuanshuo Zhang, Xiyuan Yang, Yifan Zhou, Cheng Wang, Gongyi Zou, Xianghe Pang, Wenhao Wang, Menglan Chen, Shuo Tang, Zhiyu Li, Siheng Chen
https://arxiv.org/abs/2510.02271

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require precise, domain-specific knowledge unavailable from the web. The emergence of the Model Context Protocol (MCP) now allows agents to interface with thousands of specialized tools, seemingly resolving this limitation. Yet it remains unclear whether agents can ef…

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran, Duc-Hai Nguyen, Hoang-Quoc-Viet Pham, Quan Le, Hoang Thanh Lam, Hoang D. Nguyen
https://arxiv.org/abs/2510.00023

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for coaching tool use in agentic models with flexible reinforcement learning (RL), easing the barriers for researchers and practitioners to adapt LLM-…

ARENA: A tool for measuring and analysing the energy efficiency of Android apps
Hina Anwar
https://arxiv.org/abs/2510.01754 https://arxiv.org/pdf/2510.0175…

ARENA: A tool for measuring and analysing the energy efficiency of Android apps
To build energy-efficient apps, there is a need to estimate and analyze their energy consumption in typical usage scenarios. The energy consumption of Android apps could be estimated via software-based and hardware-based approaches. Software-based approaches, while easier to implement, are not as accurate as hardware-based approaches. The process of measuring the energy consumption of an Android app via a hardware-based approach typically involves 1) setting up a measurement environment, 2) exe…

Diffraction by Circular and Triangular Apertures as a Diagnostic Tool of Twisted Matter Waves
Maksim Maksimov, Nikita Borodin, Daria Kargina, Dmitry Naumov, Dmitry Karlovets
https://arxiv.org/abs/2510.00826

Diffraction by Circular and Triangular Apertures as a Diagnostic Tool of Twisted Matter Waves
We study diffraction of twisted matter waves (electrons and light ions carrying orbital angular momentum $\ell/\hbar=0,\pm1,\pm2,\ldots$ by circular and triangular apertures. Within the scalar Kirchhoff-Fresnel framework, circular apertures preserve cylindrical symmetry and produce ringlike far-field profiles whose radii and widths depend on $|\ell|$ but are insensitive to its sign. In contrast, equilateral triangles break axial symmetry and yield structured patterns that encode both …

Building Bigraphs of the real world
Kang Rong Roy Ang
https://arxiv.org/abs/2508.00003 https://arxiv.org/pdf/2508.00003

Building Bigraphs of the real world
This report proposes a formal specification for organising all buildings, streets and administrative areas in the world into a hierarchical space-partitioning tree using data from OpenStreetMap. This hierarchical structure is encoded into a bigraph, serving as a digital twin of the world and capturing complete street connectivity. It presents a tool implemented in OCaml (source code at https://github.com/royangkr/bigraph-of-the-world ) that constructs bigraphs for regions from any part of the w…

Inference in Spreading Processes with Neural-Network Priors
Davide Ghio, Fabrizio Boncoraglio, Lenka Zdeborov\'a
https://arxiv.org/abs/2509.02073 https://

Inference in Spreading Processes with Neural-Network Priors
Stochastic processes on graphs are a powerful tool for modelling complex dynamical systems such as epidemics. A recent line of work focused on the inference problem where one aims to estimate the state of every node at every time, starting from partial observation of a subset of nodes at a subset of times. In these works, the initial state of the process was assumed to be random i.i.d. over nodes. Such an assumption may not be realistic in practice, where one may have access to a set of covaria…

Using explainable artificial intelligence (XAI) as a diagnostic tool: An application for deducing hydrologic connectivity at watershed scale
Sheng Ye, Jiyu Li, Yifan Chai, Lin Liu, Murugesu Sivapalan, Qihua Ran
https://arxiv.org/abs/2509.02127

Using explainable artificial intelligence (XAI) as a diagnostic tool: An application for deducing hydrologic connectivity at watershed scale
Explainable artificial intelligence (XAI) methods have been applied to interpret deep learning model results. However, applications that integrate XAI with established hydrologic knowledge for process understanding remain limited. Here we present a framework that apply XAI method at point-scale to provide granular interpretation and enable cross-scale aggregation of hydrologic responses. Hydrologic connectivity is used as a demonstration of the value of this approach. Soil moisture and its move…

Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions
Hun Kuk Park, Taekyung Kim, Dimitra Panagou
https://arxiv.org/abs/2510.01402

Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions
Control Barrier Functions (CBFs) are a powerful tool for ensuring the safety of autonomous systems, yet applying them to nonholonomic robots in cluttered, dynamic environments remains an open challenge. State-of-the-art methods often rely on collision-cone or velocity-obstacle constraints which, by only considering the angle of the relative velocity, are inherently conservative and can render the CBF-based quadratic program infeasible, particularly in dense scenarios. To address this issue, we …

Modelling Program Spaces in Program Synthesis with Constraints
Tilman Hinnerichs, Bart Swinkels, Jaap de Jong, Reuben Gardos Reid, Tudor Magirescu, Neil Yorke-Smith, Sebastijan Dumancic
https://arxiv.org/abs/2508.00005

Modelling Program Spaces in Program Synthesis with Constraints
A core challenge in program synthesis is taming the large space of possible programs. Since program synthesis is essentially a combinatorial search, the community has sought to leverage powerful combinatorial constraint solvers. Here, constraints are used to express the program semantics, but not as a potentially potent tool to remove unwanted programs. Recent inductive logic programming approaches introduce constraints on the program's syntax to be synthesized. These syntactic constraints allo…

ICE to Buy Tool that Tracks Locations of Hundreds of Millions of Phones Every Day
https://www.404media.co/email/0ba0f6a2-9195-4ced-9c40-92bb72367e7a/?ref=daily-stories-newsletter

Temporal Representation Learning for Real-Time Ultrasound Analysis
Yves Stebler, Thomas M. Sutter, Ece Ozkan, Julia E. Vogt
https://arxiv.org/abs/2509.01433 https://

Temporal Representation Learning for Real-Time Ultrasound Analysis
Ultrasound (US) imaging is a critical tool in medical diagnostics, offering real-time visualization of physiological processes. One of its major advantages is its ability to capture temporal dynamics, which is essential for assessing motion patterns in applications such as cardiac monitoring, fetal development, and vascular imaging. Despite its importance, current deep learning models often overlook the temporal continuity of ultrasound sequences, analyzing frames independently and missing key …

One of the rare examples where #Microsoft actually created a software itself (instead of buying some 3rd party tool embracing it) was published as open source (MIT license): https://github.com/microsoft/BASIC-M65

Czas w końcu wziąć się za przenoszenie swoich projektów z LLM Torment Nexus, dawniej #GitHub. Projekty związane z #Gentoo trafią na naszą własną infrastrukturę, w najbliższym czasie GitHub dalej będzie służył jako serwer lustrzany / ścieżka przyjmowania łatek. W przyszłości prawdopodobnie te funkcje przejmie

I thought I was going to be in luck, as there's a convenient 'Export Data' which generates a .zip containing all the source account data.
Went to the new instance expecting to import that zip, only to be greeted with 'This only supports CSV files'...
FML
SO, my current thought process is to let the new server pull in posts from the original server organically, (with help from

Duality theory of tautological systems
Paul G\"orlach, Christian Sevenheck
https://arxiv.org/abs/2510.01980 https://arxiv.org/pdf/2510.01980

Duality theory of tautological systems
We discuss the holonomic dual of tautological systems, with a view towards applications to linear free divisors and to homogeneous spaces. As a technical tool, we consider a Chevalley--Eilenberg type complex, generalizing Euler--Koszul technology from the GKZ theory, and show equivariance and holonomicity of it.

Rawgraphs is another tool to make figures without R: #dataviz #ui

RAWGraphs
A free and open source tool for data visualization.

Pilot Study on Generative AI and Critical Thinking in Higher Education Classrooms
W. F. Lamberti, S. R. Lawrence, D. White, S. Kim, S. Abdullah
https://arxiv.org/abs/2509.00167 …

Pilot Study on Generative AI and Critical Thinking in Higher Education Classrooms
Generative AI (GAI) tools have seen rapid adoption in educational settings, yet their role in fostering critical thinking remains underexplored. While previous studies have examined GAI as a tutor for specific lessons or as a tool for completing assignments, few have addressed how students critically evaluate the accuracy and appropriateness of GAI-generated responses. This pilot study investigates students' ability to apply structured critical thinking when assessing Generative AI outputs in i…

CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
Jo\~ao Valente, Atabak Dehban, Rodrigo Ventura
https://arxiv.org/abs/2508.21732

CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities across various multimodal tasks. They continue, however, to struggle with trivial scenarios such as reading values from Digital Measurement Devices (DMDs), particularly in real-world conditions involving clutter, occlusions, extreme viewpoints, and motion blur; common in head-mounted cameras and Augmented Reality (AR) applications. Motivated by these limitations, this work introduces CAD2DMD-SE…

Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
Molly Noel, Gabriel Mancino-Ball, Yangyang Xu
https://arxiv.org/abs/2508.00267 https://

Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
Graph convolutional networks (GCNs) are a powerful tool for graph representation learning. Due to the recursive neighborhood aggregations employed by GCNs, efficient training methods suffer from a lack of theoretical guarantees or are missing important practical elements from modern deep learning algorithms, such as adaptivity and momentum. In this paper, we present several neighbor-sampling (NS) based Adam-type stochastic methods for solving a nonconvex GCN training problem. We utilize the con…

ThinkBrake: Mitigating Overthinking in Tool Reasoning
Minjae Oh, Sangjun Song, Seungkyu Lee, Sungmin Jo, Yohan Jo
https://arxiv.org/abs/2510.00546 https://…

ThinkBrake: Mitigating Overthinking in Tool Reasoning
Small reasoning models (SRMs) often overthink during tool use: they reach a correct tool-argument configuration, then continue reasoning and overwrite it with an incorrect final call. We diagnose overthinking via oracle rollouts that inject at sentence boundaries. On the Berkeley Function Calling Leaderboard (BFCL), this oracle termination lifts average accuracy from 85.8\% to 94.2\% while reducing tokens by 80-94\%, revealing substantial recoverable headroom and potential redundant re…

The evolution of PUCHEROS from a basic to a competitive tool for stellar astrophysics
Luca Antonucci, Leonardo Vanzi, Abner Zapata, Mauricio Flores, Angelica Suarez, Rafael Brahm, Tzu Shen, Manuel Parra, Rafael Ormazabal, Gerardo Avila, Petr Kabath, Artie Hatzes, Pavol Gajdos, Marek Skarka, Jiri Zak, Petra Odert, Jozef Liptak, Robert Greimel, Martin Leitzinger
…

The evolution of PUCHEROS from a basic to a competitive tool for stellar astrophysics
We present PUCHEROS +, a new spectrograph developed as an enhanced version of PUCHEROS (Pontificia Universidad Catolica High Echelle Resolution Optical Spectrograph), which was the first high-resolution spectrograph built at the Pontificia Universidad Catolica de Chile (UC). With respect to its predecessor, PUCHEROS + includes a substantial number of improvements, mainly: a new scientific detector, improved objective optics, calibration system, guiding, active thermal control, and remote observ…

ICE to Buy Tool that Tracks Locations of Hundreds of Millions of Phones Every Day https://www.404media.co/ice-to-buy-tool-that-tracks-locations-of-hundreds-of-millions-of-phones-every-day/

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao
https://arxiv.org/abs/2510.00967

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the…

Sources: Apple plans an AI search tool, World Knowledge Answers, for spring 2026 as part of a Siri revamp; Apple and Google plan to test a Google model for Siri (Mark Gurman/Bloomberg)
https://www.bloomberg.com/news/articles/20

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
Yanxu Chen, Zijun Yao, Yantao Liu, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li
https://arxiv.org/abs/2510.02209

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, bu…

Tool verrät, welche KI-Skills im Arbeitsmarkt wirklich gefragt sind
Welche KI-Kompetenzen sind wirklich relevant? Ein neues Tool analysiert Stellenangebote und zeigt, wo Unternehmen aktuell Bedarf haben.

as_skitter: Skitter IP graph (2005)
An aggregate snapshot of the Internet Protocol (IP) graph, as measured by the traceroute tool on CAIDA's skitter infrastructure, in 2005.
This network has 1696415 nodes and 11095298 edges.
Tags: Technological, Communication, Unweighted
https://networks.skewed.de/net/as_s…

Hybrid biphoton spectrometer for time-resolved quantum spectroscopy across visible and near-infrared regions
Ozora Iso, Koya Onoda, Nicola J. Fairbairn, Masahiro Yabuno, Hirotaka Terai, Shigehito Miki, Ryosuke Shimizu
https://arxiv.org/abs/2510.01836

Hybrid biphoton spectrometer for time-resolved quantum spectroscopy across visible and near-infrared regions
Joint spectral measurements are a powerful tool for characterising biphoton spectral correlation, which is crucial for quantum information and communication technologies. In these applications, highly pure biphoton states are essential in any time- and frequency-mode, often obviating the need for time-resolved measurements. Conversely, spectroscopy utilising entangled photon pairs is gaining significant attention for its ability to unveil molecular dynamics, a field that critically demands time…

Probit Monotone BART
Jared D. Fisher
https://arxiv.org/abs/2509.00263 https://arxiv.org/pdf/2509.00263

Probit Monotone BART
Bayesian Additive Regression Trees (BART) of Chipman et al. (2010) has proven to be a powerful tool for nonparametric modeling and prediction. Monotone BART (Chipman et al., 2022) is a recent development that allows BART to be more precise in estimating monotonic functions. We further these developments by proposing probit monotone BART, which allows the monotone BART framework to estimate conditional mean functions when the outcome variable is binary.

Systematic Evaluation of Trade-Offs in Motion Planning Algorithms for Optimal Industrial Robotic Work Cell Design
G. de Mathelin, C. Hartl-Nesic, A. Kugi
https://arxiv.org/abs/2509.02146

Systematic Evaluation of Trade-Offs in Motion Planning Algorithms for Optimal Industrial Robotic Work Cell Design
The performance of industrial robotic work cells depends on optimizing various hyperparameters referring to the cell layout, such as robot base placement, tool placement, and kinematic design. Achieving this requires a bilevel optimization approach, where the high-level optimization adjusts these hyperparameters, and the low-level optimization computes robot motions. However, computing the optimal robot motion is computationally infeasible, introducing trade-offs in motion planning to make the …

Roblox restricts some features in the UAE and Saudi Arabia, including its in-game chat tool, and improves Arabic content moderation over child safety concerns (Leen Al-Rashdan/Bloomberg)
https://www.bloomberg.com/news/articles/20

An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence
Conall Daly, Darren Ramsook, Anil Kokaram
https://arxiv.org/abs/2510.01361 https://

An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence
Video frame interpolation is a fundamental tool for temporal video enhancement, but existing quality metrics struggle to evaluate the perceptual impact of interpolation artefacts effectively. Metrics like PSNR, SSIM and LPIPS ignore temporal coherence. State-of-the-art quality metrics tailored towards video frame interpolation, like FloLPIPS, have been developed but suffer from computational inefficiency that limits their practical application. We present $\text{PSNR}_{\text{DIV}}$, a novel ful…

Generalization of Variadic Structures with Binders: A Tool for Structural Code Comparison
Alexander Baumgartner, Temur Kutsia
https://arxiv.org/abs/2509.25023 https://

Generalization of Variadic Structures with Binders: A Tool for Structural Code Comparison
This paper introduces a novel anti-unification algorithm for the generalization of variadic structures with binders, designed as a flexible tool for structural code comparison. By combining nominal techniques for handling variable binding with support for variadic expressions (common in abstract syntax trees and programming languages), the approach addresses key challenges such as overemphasis on bound variable names and difficulty handling insertions or deletions in code fragments. The algorit…

from my link log —
wtfis: Passive hostname, domain and IP lookup tool for non-robots.
https://github.com/pirxthepilot/wtfis
saved 2025-05-13 https://

GitHub - pirxthepilot/wtfis: Passive hostname, domain and IP lookup tool for non-robots
Passive hostname, domain and IP lookup tool for non-robots - pirxthepilot/wtfis

Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
Matte Lim, Catherine Yeh, Martin Wattenberg, Fernanda Vi\'egas, Panagiotis Michalatos
https://arxiv.org/abs/2509.01051

Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
Many real-world datasets -- from an artist's body of work to a person's social media history -- exhibit meaningful semantic changes over time that are difficult to capture with existing dimensionality reduction methods. To address this gap, we introduce a visualization technique that combines force-based projection and streaming clustering methods to build a spatial-temporal map of embeddings. Applying this technique, we create Chronotome, a tool for interactively exploring evolving themes in t…

Crosslisted article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[2/2]:
- Scaffolding Collaborative Learning in STEM: A Two-Year Evaluation of a Tool-Integrated Project-Ba...
Caterina Fuster-Barcelo, Gonzalo R. Rios-Munoz, Arrate Munoz-Barrutia

Open-source AdaptixC2 hacking tool has fans in Russian cybercrime underground https://therecord.media/open-source-adaptixc2-red-teaming-tool-russian-cybercrime

CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
Daniele Bifolco, Guido Annicchiarico, Pierluigi Barbiero, Massimiliano Di Penta, Fiorella Zampetti
https://arxiv.org/abs/2510.01077

CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
Large Language Models (LLMs) are widely used in software development tasks nowadays. Unlike reusing code taken from the Web, for LLMs' generated code, developers are concerned about its lack of trustworthiness and possible copyright or licensing violations, due to the lack of code provenance information. This paper proposes CodeGenLink, a GitHub CoPilot extension for Visual Studio Code aimed at (i) suggesting links containing code very similar to automatically generated code, and (ii) whenever …

Stripe launches Open Issuance, a stablecoin issuance platform built on Stripe's Bridge, which lets companies create their own stablecoins with minimal coding (Krisztian Sandor/CoinDesk)
https://www.coindesk.com/business/2025/…

Stripe Unveils Stablecoin Issuance Tool With Phantom's Token, Expands Into AI Commerce with OpenAI
With Open Issuance and AI payment standards, Stripe is doubling down on its bet on the rising role of blockchain and digital agents in payments.

Close encounters between periodic light and periodic arrays of quantum emitters
Frieder Lindel, Carlos J. S\'anchez Mart\'inez, Johannes Feist, Francisco J. Garc\'ia-Vidal
https://arxiv.org/abs/2508.00797

Close encounters between periodic light and periodic arrays of quantum emitters
Periodically structured surfaces (metasurfaces), i.e., periodic light, have evolved as a powerful tool for manipulating electromagnetic fields both in classical and quantum regimes. However, no general approach for quantizing the electromagnetic fields and treating quantum light-matter interactions in such structures exists. Here, we construct an ab initio few-mode quantization scheme for metasurface resonances based on macroscopic quantum electrodynamics. We use our approach to propose a frame…

YouTubes neues Tool zur Gesichtserkennung soll KI-Deepfakes unterbinden
Content-Ersteller können bei YouTube nach KI-Deepfakes ihrer Person suchen und solche Videos entfernen lassen. Dafür benötigt YouTube Ausweis und Gesichtsvideo.

Tencent releases HunyuanWorld-Voyager, an open-weights AI model that generates 3D-consistent video sequences from a single image, trained on 100K video clips (Benj Edwards/Ars Technica)
https://arstechnica.com/ai/2025/09/new-ai-model-turn…

New AI model turns photos into explorable 3D worlds, with caveats
Openly available AI tool creates steerable 3D-like video, but requires serious GPU muscle.

DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
Jialin Gao, Donghao Zhou, Mingjian Liang, Lihao Liu, Chi-Wing Fu, Xiaowei Hu, Pheng-Ann Heng
https://arxiv.org/abs/2510.02178

DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
3D indoor layout synthesis is crucial for creating virtual environments. Traditional methods struggle with generalization due to fixed datasets. While recent LLM and VLM-based approaches offer improved semantic richness, they often lack robust and flexible refinement, resulting in suboptimal layouts. We develop DisCo-Layout, a novel framework that disentangles and coordinates physical and semantic refinement. For independent refinement, our Semantic Refinement Tool (SRT) corrects abstract objec…

Resting-state fMRI Analysis using Quantum Time-series Transformer
Junghoon Justin Park, Jungwoo Seo, Sangyoon Bae, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Jiook Cha, Shinjae Yoo
https://arxiv.org/abs/2509.00711

Resting-state fMRI Analysis using Quantum Time-series Transformer
Resting-state functional magnetic resonance imaging (fMRI) has emerged as a pivotal tool for revealing intrinsic brain network connectivity and identifying neural biomarkers of neuropsychiatric conditions. However, classical self-attention transformer models--despite their formidable representational power--struggle with quadratic complexity, large parameter counts, and substantial data requirements. To address these barriers, we introduce a Quantum Time-series Transformer, a novel quantum-enha…

PyTrim: A Practical Tool for Reducing Python Dependency Bloat
Konstantinos Karakatsanis, Georgios Alexopoulos, Ioannis Karyotakis, Foivos Timotheos Proestakis, Evangelos Talos, Panos Louridas, Dimitris Mitropoulos
https://arxiv.org/abs/2510.00674

PyTrim: A Practical Tool for Reducing Python Dependency Bloat
Dependency bloat is a persistent challenge in Python projects, which increases maintenance costs and security risks. While numerous tools exist for detecting unused dependencies in Python, removing these dependencies across the source code and configuration files of a project requires manual effort and expertise. To tackle this challenge we introduce PYTRIM, an end-to-end system to automate this process. PYTRIM eliminates unused imports and package declarations across a variety of file types,…

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao
https://arxiv.org/abs/2510.00967

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the…

Microsoft-Insider-Vorschauen: Snipping-Tool kann Fenster-Videos aufnehmen
Microsoft hat neue Windows-Vorschauen in den Insider-Kanälen veröffentlicht. Sie bringen neue Funktionen fürs Snipping-Tool und KI-Features.

Hybrid quantum memory leveraging slow-light and gradient-echo duality
Stanis{\l}aw Kurzyna, Mateusz Mazelanik, Wojciech Wasilewski, Micha{\l} Parniak
https://arxiv.org/abs/2509.02810

Hybrid quantum memory leveraging slow-light and gradient-echo duality
We demonstrate a hybrid quantum memory that combines Gradient Echo Memory (GEM) and Electromagnetically Induced Transparency (EIT) protocols for reversible mapping between light and atomic coherence. By leveraging GEM and EIT complementarity, we realize time-to-frequency and frequency-to-time conversion mechanisms for spectro-temporal modes. This capability provides a versatile tool for quantum communication, where coherent frequency-time conversion enhances network interoperability. In additio…

JS-TOD: Detecting Order-Dependent Flaky Tests in Jest
Negar Hashemi, Amjed Tahir, Shawn Rasheed, August Shi, Rachel Blagojevic
https://arxiv.org/abs/2509.00466 https://

JS-TOD: Detecting Order-Dependent Flaky Tests in Jest
We present JS-TOD (JavaScript Test Order-dependency Detector), a tool that can extract, reorder, and rerun Jest tests to reveal possible order-dependent test flakiness. Test order dependency is one of the leading causes of test flakiness. Ideally, each test should operate in isolation and yield consistent results no matter the sequence in which tests are run. However, in practice, test outcomes can vary depending on their execution order. JS-TOD employed a systematic approach to randomising tes…

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
Jinzhou Tang, Jusheng Zhang, Qinhan Lv, Sidi Liu, Jing Yang, Chengpei Tang, Keze Wang
https://arxiv.org/abs/2509.00189

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one hand, reusable fixed workflows require manual reconfiguration upon environmental changes; on the other hand, flexible reactive loops fail to distill reasoning progress into transferable structures. We introduce Hierarchical Variable Agent (HiVA), a novel framew…

eHealth: TI-Monitoring-Alternative zeigt Live-Status & Historie von TI-Störungen
Ein Open-Source-Tool schafft mehr Transparenz bei technischen Störungen im digitalen Gesundheitswesen. Im Gespräch erklärt der Entwickler seine Motivation.

Git Context Controller: Manage the Context of LLM-based Agents like Git
Junde Wu
https://arxiv.org/abs/2508.00031 https://arxiv.org/pdf/2508.00031

Git Context Controller: Manage the Context of LLM-based Agents like Git
Large language model (LLM) based agents have shown impressive capabilities by interleaving internal reasoning with external tool use. However, as these agents are deployed in long-horizon workflows, such as coding for a big, long-term project, context management becomes a critical bottleneck. We introduce Git-Context-Controller (GCC), a structured context management framework inspired by software version control systems. GCC elevates context as versioned memory hierarchy like Git. It structures…

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
Seunghoo Hong, Geonho Son, Juhun Lee, Simon S. Woo
https://arxiv.org/abs/2510.00778 https://

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A direct inheriting application of this inversion operation is real image editing, where the inversion yields latent trajectories to be utilized during the synthesis of the edited image. Unfortunately, this practical tool has enabled malicious users to freely …

Salesforce launches Agentforce Vibes, an enterprise vibe-coding tool and IDE featuring Vibe Codey, built on a fork from Cline's open source AI coding agent (Rebecca Szkutak/TechCrunch)
https://techcrunch.com/2025/10/01/salesforce-lau…

Salesforce launches enterprise vibe-coding product, Agentforce Vibes | TechCrunch
Salesforce is also releasing a vibe-coding agent named Vibe Codey to help companies foray into vibe coding with enterprise security.

How Quantization Impacts Privacy Risk on LLMs for Code?
Md Nazmul Haque, Hua Yang, Zhou Yang, Bowen Xu
https://arxiv.org/abs/2508.00128 https://arxiv.org/p…

How Quantization Impacts Privacy Risk on LLMs for Code?
Large language models for code (LLMs4Code) rely heavily on massive training data, including sensitive data, such as cloud service credentials of the projects and personal identifiable information of the developers, raising serious privacy concerns. Membership inference (MI) has recently emerged as an effective tool for assessing privacy risk by identifying whether specific data belong to a model's training set. In parallel, model compression techniques, especially quantization, have gained trac…

Anthropic adds context editing and a memory tool to the Claude API, allowing AI agents to handle long-running tasks without frequently hitting context limits (Anthropic)
https://www.anthropic.com/news/context-management

Managing context on the Claude Developer Platform
We're introducing new capabilities for managing your agents’ context on the Claude Developer Platform: context editing and the memory tool.

Automated Generation of Issue-Reproducing Tests by Combining LLMs and Search-Based Testing
Konstantinos Kitsios, Marco Castelluccio, Alberto Bacchelli
https://arxiv.org/abs/2509.01616

Automated Generation of Issue-Reproducing Tests by Combining LLMs and Search-Based Testing
Issue-reproducing tests fail on buggy code and pass once a patch is applied, thus increasing developers' confidence that the issue has been resolved and will not be re-introduced. However, past research has shown that developers often commit patches without such tests, making the automated generation of issue-reproducing tests an area of interest. We propose BLAST, a tool for automatically generating issue-reproducing tests from issue-patch pairs by combining LLMs and search-based software test…

MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Khaled Ahmed, Jialing Song, Boqi Chen, Ou Wei, Bingzhou Zheng
https://arxiv.org/abs/2508.00630 https://…

MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of automatic model correctness evaluation tools. Such a tool can be used to evaluate both manually and AI …

Grammarly rebrands as Superhuman after its acquisitions of Superhuman Mail in June and Coda in December 2024; the standalone writing tool Grammarly still exists (Stevie Bonifield/The Verge)
https://www.theverge.com/news/808472/grammarly-superhuman-ai-rebrand-rel…

Grammarly is changing its name to Superhuman
Grammarly is rebranding to become Superhuman, an AI agent-powered work platform that combines its writing tool with Coda and Superhuman Mail.