📌 TOPINDIATOURS Eksklusif ai: There’s Reportedly a Car Secretly Following Every Te

When Tesla launched its Robotaxi service last summer, it came with an embarrassing caveat. Sitting in the front of each of the vehicles were human “safety monitors” who stuck out like sore thumbs — contradicting CEO Elon Musk’s promises that the service would hit the road fully driverless. That the silent human employees sat in the front passenger seat, instead of the driver’s, only served to further underscore how Musk had speciously weaseled his way out being true to his word.

Now, over half a year into the service’s launch, Musk insists that Robotaxis will start giving rides in Austin, Texas “with no safety monitor in the car,” he announced on his website X on Thursday. This comes about a month after fans spotted several of the cabs driving around without any occupants, prompting Musk to confirm that fully driverless testing was underway.

But hold your horses and runaway self-driving cars, because this appears to be another bit of deception. The EV blog Electrek reports that instead of supervising from inside the vehicle, it now appears that the safety monitors are simply watching from a car that follows the Robotaxis throughout their entire trips — a Rube Goldberg-style workaround that illustrates the lengths Musk will go to keep up a charade of progress. 

According to Electrek, this new operating procedure can be seen in a vlog shared by Tesla enthusiast Joe Tegtmeyer on Thursday, which shows two black Teslas conspicuously tailing the red Robotaxi. Tegtmeyer himself comments on it during the video, calling them a “chase car” that he suspects are there for “validation.”

Tesla has struggled to refine its self-driving technology, including its Robotaxi software. The driverless-but-not-quite-superviserless cabs have already gotten into numerous accidents, have been spotted ignoring speed limits and other traffic laws, on top of instances of driving dangerously or erratically. The human monitors have also been forced to make interventions to prevent a potential accident, and have even at times taken complete control of the vehicles.

Musk once said Tesla was being “paranoid” about Robotaxi safety, and the automaker is clearly caught in a tug of war in which it knows that its tech isn’t ready for primetime, but also has to show some semblance of keeping up with Musk’s promised timelines, which include claiming that the Robotaxi service would have over 1,000 cars in its fleet “within a few months” — it currently only has around 30 — and that over a million self-driving Teslas would be deployed across the US by the end of 2026.

His latest announcement only highlighted that there was “no safety monitor in the car” and made no mention of the tailing vehicles. While you can’t fault Tesla for going the safe route by still supervising its cabs, absurd as its new methods are, it’s clearly misleading its fans and investors into thinking it’s on the pathway to full autonomy. Having an extra vehicle tail every Robotaxi obviously can’t be scaled up if those promised thousands end up roaming cities across the country.

More on Tesla: Tesla Cybercab Spotted Dripping Liquid

The post There’s Reportedly a Car Secretly Following Every Tesla Robotaxi, and the Reason Why Is So Absurd You Aren’t Going to Believe It appeared first on Futurism.

🔗 Sumber: futurism.com

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

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