📌 TOPINDIATOURS Hot ai: Justice Department Humiliated as People Find the Epstein F

Many were disappointed — though perhaps not surprised — when the Justice Department’s long-awaited document dump on its investigation into Jeffrey Epstein came heavily redacted.

Or at least, they were supposed to be redacted. As documents continued to be released to the public starting last Friday, some netizens quickly noticed that a lot of the blacked-out text could be recovered with the super elite hacking trick of highlighting the redacted paragraphs and copying them into another document, The Guardian reports. A cybersecurity expert, Chad Loder, also says he was able to uncover even more redacted portions with some more sophisticated “PDF forensics,” including what appears to be a photo of Epstein’s cell door marked off with crime scene tape.

The New York Times reported that none of the failed redactions tell us anything new about president Donald Trump’s deep ties to Epstein, but they do detail how Epstein’s henchmen, Darren K. Indyke and Richard D. Kahn, helped him lure in underaged girls to sexually abuse them.

According to the un-redacted filings from a civil case in the Virgin Islands against Indyke and Kahn, “between September 2015 and June 2019, Indyke signed (FAC) for over $400,000 made payable to young female models and actresses, including a former Russian model who received over $380,000 through monthly payments of $8,333 made over a period of more than three and a half years until the middle of 2019.”

Redacted portions also detail how Epstein covered his tracks by paying hush money to witnesses, threatening to harm the victims, and releasing “damaging stories about them to damage their credibility when they tried to go public with their stories of being trafficked and sexually abused.” He also instructed “participant-witnesses to destroy evidence relevant to ongoing court proceedings involving Defendants’ criminal sex trafficking and abuse conduct.”

It’s not clear why these portions were — unsuccessfully — redacted. The Epstein Files Transparency Act under which the documents are being released, The Guardian notes, allows the DoJ to “withhold certain information such as the personal information of victims and materials that would jeopardize an active federal investigation.”

The botched redaction job is a huge embarrassment for the Trump administration, which has come under fire for its hesitancy to release Epstein case files to the public, something that Trump had earlier promised he would do. In February, it tepidly released files that detailed little that wasn’t already publicly known, and sparked outrage in July when the DoJ said it would no longer release additional files to the public. It’s backtracked on that stance, but has aroused suspicion with its efforts to censor some of the new documents. In addition to the redactions, over a dozen photos were removed from the initial release, including a photo of Trump alongside Epstein. The delayed release of the documents also missed a legally-binding deadline set by Congress.

None of this looks good for the president, but no matter. In an official statement posted on X, the DoJ said that anything in the Epstein files that makes Trump look bad are “sensationalist” lies.

“Some of these documents contain untrue and sensationalist claims made against President Trump that were submitted to the FBI right before the 2020 election,” the DoJ statement read. “To be clear: the claims are unfounded and false, and if they had a shred of credibility, they certainly would have been weaponized against President Trump already.”

More on Epstein: New Photos Show That Epstein’s Island Contained the Creepiest Dentist’s Facility We’ve Ever Seen

The post Justice Department Humiliated as People Find the Epstein Files Can Easily Be Un-Redacted appeared first on Futurism.

🔗 Sumber: futurism.com

📌 TOPINDIATOURS Hot ai: Which Agent Causes Task Failures and When?Researchers from

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