📌 TOPINDIATOURS Eksklusif ai: Microsoft Realizes It’s Epically Screwed Up Windows

Microsoft’s commitment to shoving its Copilot AI chatbot into every imaginable facet of its widely-used Windows operating system hasn’t gone over well with users.

Copilot feels like it’s infiltrated everything, from a dedicated keyboard key to a thick coat of AI weighing down its otherwise lightweight text editor, Notepad. And that’s not to mention years of annoying ads for its in-house services, like OneDrive and Microsoft 365.

In short, it’s no wonder users are desperately looking for greener pastures, from a growing exodus trying out the open source operating system Linux and Apple’s aggressively priced MacBook Neo, which could be the non-Windows saving grace for many budget-conscious buyers looking for a basic machine.

Microsoft seems to have finally noticed that its house is on fire, particularly following the heavy-handed embrace of AI garnering it the widely used pejorative of “Microslop.” Unsubstantiated rumors over Windows 12 embracing AI even more triggered a massive uproar earlier this month, once again highlighting widespread disillusionment.

In a Friday post titled “Our commitment to Windows quality,” Windows VP Pavan Davuluri effectively admitted outright that the company has gone too far shoving AI down users’ throats at all costs.

“Every day, we hear from the community about how you experience Windows,” he wrote, in gloriously euphemistic style. “And over the past several months, the team and I have spent a great deal of time analyzing your feedback. What came through was the voice of people who care deeply about Windows and want it to be better.”

Apart from announcing astonishingly basic functionality like allowing the taskbar to be pinned to the left or right of the screen — something other operating systems have been capable of for decades — Davuluri claimed that “you will see us be more intentional about how and where Copilot integrates across Windows, focusing on experiences that are genuinely useful and well‑crafted.”

“As part of this, we are reducing unnecessary Copilot entry points, starting with apps like Snipping Tool, Photos, Widgets and Notepad,” he wrote.

The admission shows how companies are still desperately searching for meaningful ways to implement large language model-based tech in consumer products. As AI industry leaders continue to pour hundreds of billions of dollars into the tech, many attempts to embrace the tech are backfiring in spectacular fashion, leading to frustration and backlash among many who never asked for these changes.

It’s not just users becoming annoyed. Some implementations of AI could lead to real cybersecurity issues. Case in point, after Microsoft crammed its Copilot into the Notepad app, researchers discovered a major security failure that had to be patched.

Davuluri also promised faster search, a more reliable File Explorer — the app that allows users to access their files, which has slowed down significantly over the last couple of updates — and reduced memory usage.

But whether we should take him at his word will ultimately be up to the many disenfranchised Windows users who have had to deal with a lackluster experience for years now.

For one, Davuluri’s carefully worded promise of being “more intentional” about shoehorning Copilot into the software leaves plenty of opportunities for them to continue burdening the operating system with more AI.

Meanwhile, the team continues to be forced to put out fires, like a widespread bug that caused major Microsoft account sign-in issues over the weekend following the rollout of a flawed update.

More on Windows: Drama Erupts Over Claims That Microsoft Will Embrace AI Even More Drastically in Windows 12

The post Microsoft Realizes It’s Epically Screwed Up Windows 11 as Users Rage at Copilot AI Crammed Everywhere appeared first on Futurism.

🔗 Sumber: futurism.com

📌 TOPINDIATOURS Eksklusif ai: Which Agent Causes Task Failures and When?Researcher

Share My Research is Synced’s column that welcomes scholars to share their own research breakthroughs with over 1.5M global AI enthusiasts. Beyond technological advances, Share My Research also calls for interesting stories behind the research and exciting research ideas. Contact us: chain.zhang@jiqizhixin.com

Meet the authors
Institutions: Penn State University, Duke University, Google DeepMind, University of Washington, Meta, Nanyang Technological University, and Oregon State University. The co-first authors are Shaokun Zhang of Penn State University and Ming Yin of Duke University.

In recent years, LLM Multi-Agent systems have garnered widespread attention for their collaborative approach to solving complex problems. However, it’s a common scenario for these systems to fail at a task despite a flurry of activity. This leaves developers with a critical question: which agent, at what point, was responsible for the failure? Sifting through vast interaction logs to pinpoint the root cause feels like finding a needle in a haystack—a time-consuming and labor-intensive effort.
 
This is a familiar frustration for developers. In increasingly complex Multi-Agent systems, failures are not only common but also incredibly difficult to diagnose due to the autonomous nature of agent collaboration and long information chains. Without a way to quickly identify the source of a failure, system iteration and optimization grind to a halt.
 
To address this challenge, researchers from Penn State University and Duke University, in collaboration with institutions including Google DeepMind, have introduced the novel research problem of “Automated Failure Attribution.” They have constructed the first benchmark dataset for this task, Who&When, and have developed and evaluated several automated attribution methods. This work not only highlights the complexity of the task but also paves a new path toward enhancing the reliability of LLM Multi-Agent systems.

The paper has been accepted as a Spotlight presentation at the top-tier machine learning conference, ICML 2025, and the code and dataset are now fully open-source.

Paper：https://arxiv.org/pdf/2505.00212
Code：https://github.com/mingyin1/Agents_Failure_Attribution
Dataset：https://huggingface.co/datasets/Kevin355/Who_and_When
 
 
Research Background and Challenges
LLM-driven Multi-Agent systems have demonstrated immense potential across many domains. However, these systems are fragile; errors by a single agent, misunderstandings between agents, or mistakes in information transmission can lead to the failure of the entire task.

Currently, when a system fails, developers are often left with manual and inefficient methods for debugging:
Manual Log Archaeology : Developers must manually review lengthy interaction logs to find the source of the problem.
Reliance on Expertise : The debugging process is highly dependent on the developer’s deep understanding of the system and the task at hand.
 
This “needle in a haystack” approach to debugging is not only inefficient but also severely hinders rapid system iteration and the improvement of system reliability. There is an urgent need for an automated, systematic method to pinpoint the cause of failures, effectively bridging the gap between “evaluation results” and “system improvement.”

Core Contributions
This paper makes several groundbreaking contributions to address the challenges above:
1. Defining a New Problem: The paper is the first to formalize “automated failure attribution” as a specific research task. This task is defined by identifying the failure-responsible agent and the decisive error step that led to the task’s failure.
2. Constructing the First Benchmark Dataset: Who&When : This dataset includes a wide range of failure logs collected from 127 LLM Multi-Agent systems, which were either algorithmically generated or hand-crafted by experts to ensure realism and diversity. Each failure log is accompanied by fine-grained human annotations for:
Who: The agent responsible for the failure.
When: The specific interaction step where the decisive error occurred.
Why: A natural language explanation of the cause of the failure.

3. Exploring Initial “Automated Attribution” Methods : Using the Who&When dataset, the paper designs and assesses three distinct methods for automated failure attribution:
– All-at-Once: This method provides the LLM with the user query and the complete failure log, asking it to identify the responsible agent and the decisive error step in a single pass. While cost-effective, it may struggle to pinpoint precise errors in long contexts.
– Step-by-Step: This approach mimics manual debugging by having the LLM review the interaction log sequentially, making a judgment at each step until the error is found. It is more precise at locating the error step but incurs higher costs and risks accumulating errors.
– Binary Search: A compromise between the first two methods, this strategy repeatedly divides the log in half, using the LLM to determine which segment contains the error. It then recursively searches the identified segment, offering a balance of cost and performance.

Experimental Results and Key Findings 
Experiments were conducted in two settings: one where the LLM knows the ground truth answer to the problem the Multi-Agent system is trying to solve (With Ground Truth) and one where it does not (Without Ground Truth). The primary model used was GPT-4o, though other models were also tested. The systematic evaluation of these methods on the Who&When dataset yielded several important insights:
– A Long Way to Go: Current methods are far from perfect. Even the best-performing single method achieved an accuracy of only about 53.5% in identifying the responsible agent and a mere 14.2% in pinpointing the exact error step. Some methods performed even worse than random guessing, underscoring the difficulty of the task.
– No “All-in-One” Solution: Different methods excel at different aspects of the problem. The All-at-Once method is better at identifying “Who,” while the Step-by-Step method is more effective at determining “When.” The Binary Search method provides a middle-ground performance.
 

– Hybrid Approaches Show Promise but at a High Cost: The researchers found that combining different methods, such as using the All-at-Once approach to identify a potential agent and then applying the Step-by-Step method to find the error, can improve overall performance. However, this comes with a significant increase in computational cost.

– State-of-the-Art Models Struggle: Surprisingly, even the most advanced reasoning models, like OpenAI o1 and DeepSeek R1, find this task challenging.- This h…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com