📌 TOPINDIATOURS Update ai: Data Centers in Space Are Even More Cursed Than Previou

Elon Musk and other AI leaders have repeatedly insisted that the solution to the industry’s extremely costly and energy-intensive data centers is to launch them into space, taking advantage of unfettered access to solar energy and virtually limitless real estate.

Late last month, SpaceX — now merged with xAI — filed a patent for an orbital data center constellation with the Federal Communications Commission. The idea is to have up to one million satellites circle the Earth at altitudes between 310 and 1,200 miles at a Sun-synchronous orbit to maximize the amount of solar energy captured.

The application didn’t elaborate on any of the specifics, suggesting SpaceX had only begun to ponder the idea. That’s despite Musk promising that space-based data centers could overtake their Earthbound counterparts as the most affordable way to power AI within just three years — likely yet another one of his characteristically overambitious timelines.

Many experts remain highly skeptical, questioning the financial feasibility and the technological limitations of running data centers in space.

And as Rebekah Reed — former NASA associate director and Harvard University associate director of the Program on Emerging Technology, Scientific Advancement, and Global Policy — argued in an essay for the Financial Times, it may be an even more cursed idea than we initially thought, pointing out considerable environmental concerns, on top of glaring questions regarding costs and operations.

“Treating orbit as a workaround for AI’s current energy-hungry training needs is, as OpenAI co-founder Sam Altman recently put it, ‘ridiculous,’” she wrote. “Orbital data centers are many years, perhaps decades, away.”

While Google CEO Sundar Pichai has predicted we’re only a decade away from orbital data centers, Altman ridiculed the idea, arguing during a recent conference that we’re simply “not there yet.”

Reed made the case that launching all of that mass into orbit would be prohibitively expensive. To become “economically viable”would require costs to fall below $200 per kilogram, a “sevenfold reduction from current levels.”

“That threshold isn’t expected until the mid-2030s,” she wrote.

Then there’s the issue of maintenance. In case a chip were to malfunction — or inevitably become obsolete — there’s a simple fix like sending an IT technician to rectify the issue.

“In orbit, that task requires either sophisticated in-space servicing or acceptance of degrading performance and stranded capital that becomes orbital debris as components age and fail,” Reed wrote.

Worse yet, falling satellites could inject harmful pollutants, including metals, into the upper atmosphere, an environmental toll scientists are still racing to understand.

Reed pointed to recent findings by researchers at Saarland University, Germany, who found that the carbon footprint of space data centers could exceed that of terrestrial data centers when taking manufacturing, launch, and disposal into consideration.

“Results show that, even under optimistic assumptions, in-orbit systems incur significantly higher carbon costs — up to an order of magnitude more than terrestrial equivalents — primarily due to embodied emissions from launch and re-entry,” they wrote in a yet-to-be-peer-reviewed paper last year.

Finally, an enormous orbital data center constellation of thousands of satellites could further clutter the Earth’s orbit, raising the “risk of collisions and debris, threatening communications, weather and navigation services,” Reed concluded. “Scaling data centers to match terrestrial demand would accelerate congestion and degrade the night sky.”

More on orbital data centers: Erratic Elon Musk Tells Employees to Build Massive Catapult on Moon

The post Data Centers in Space Are Even More Cursed Than Previously Believed appeared first on Futurism.

🔗 Sumber: futurism.com

📌 TOPINDIATOURS Update ai: Which Agent Causes Task Failures and When?Researchers f

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