📌 TOPINDIATOURS Update ai: Strange Mushroom Makes You See Tiny People Chilling on

Magic mushrooms, an informal group of fungi that contain the naturally occurring psychedelic substance psilocybin, are known for inducing powerful hallucinations. They can induce feelings of euphoria, a sense of belonging in the world, and distort reality by messing with the brain’s visual cortex, turning the world into a trippy, shimmering pocket dimension full of pulsating geometric patterns.

Now we’re hearing about a lesser-known species, known for its umami-forward flavor in China, which can induce far more specific hallucinations — when not prepared correctly by a chef, that is.

As the BBC reports, the mushroom, Lanmaoa asiatica, can cause you to see countless tiny people everywhere you look. Doctors in the Yunnan province of China are treating hundreds of cases a year of people having visions of small, “pint-sized, elf-like figures” crawling around and climbing up walls.

“At a mushroom hot pot restaurant there, the server set a timer for 15 minutes and warned us, ‘Don’t eat it until the timer goes off or you might see little people,’” University of Utah doctoral candidate in biology Colin Domnauer told the broadcaster.

“It seems like very common knowledge in the culture there,” he added.

The hallucinations can last a very long time, up to three days after a 12-to-24-hour onset, and often result in hospitalizations. That’s considerably longer and more severe than the average psilocybin trip.

“One elder tribesman in Papua New Guinea describes this effect, explaining how ‘he saw tiny people with mushrooms around their faces. They were teasing him, and he was trying to chase them away,’” Donmauer wrote in a November piece for the University of Utah.

“When I lifted the tablecloth higher, the heads came off and stuck to the bottom of the cloth and the bodies kept marching in place… I did this many times, at two-minute intervals, and each time they were there, marching and grinning… I measured them, too… they were [one inch] high,” a professor in Yunnan told Donmauer, recounting his own trip.

Domnauerhas been trying to hunt down the origins of the mushroom and investigate how it affects the brain, producing such surprisingly similar hallucinations in different people.

“It sounded so bizarre that there could be a mushroom out there causing fairytale-like visions reported across cultures and time,” he told the BBC. “I was perplexed and driven by curiosity to find out more.”

The appearance of tiny humans after ingesting the mushrooms does appear in academic literature, describing them as “liliputian hallucinations,” or “elusive little people.”

Even Albert Hofmann, the Swiss chemist known for being the first to synthesize, ingest, and learn about the effects of lysergic acid diethylamide (LSD), failed to identify the molecules that caused the mysterious hallucinations.

The mushrooms got their formal Latin name in 2015, yet many questions remain about their psychedelic qualities, a gap Donmauer is hoping to fill with his research.

In experiments involving mice, he found that the animals fell into a stupor after being administered extracts of the mushroom.

Donmauer has also determined that the L. asiatica mushrooms do not contain psilocybin, the substance that gives magic mushrooms their hallucinogenic qualities.

The main thing that sets it apart is that trips don’t vary greatly depending on the individual, unlike those triggered by psilocybin which can differ greatly.

The “perception of little people is very reliably and repeatedly reported,” Donmauer told the BBC. “I don’t know of anything else that produces such consistent hallucinations.”

The researcher has yet to eat the mushroom himself. Given the length of the trips and the chances of being hospitalized, we can’t blame him.

“While many questions remain, one thing is for certain: Lanmaoa asiatica reminds us that the world of mushrooms, even those found in markets and on dinner plates, conceals mysteries and wonders we’ve yet to imagine,” Donmauer wrote in his piece for the University of Utah.

“Somewhere between traditional folklore and modern biology, between the wild forest floor and the sterile scientific laboratory, lies a story still unfolding, a story that may begin with something as seemingly innocuous as a bowl of mushroom soup,” he added.

More on magic mushrooms: Evidence Grows That Tripping on Shrooms Might Increase Your Lifespan

The post Strange Mushroom Makes You See Tiny People Chilling on Every Surface 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