Go Touch Some Grass

Sensei sent FikAi out to touch grass — and to bring back the harvest. (Would've said the hunt, but it's grass.) Here's what our guy found for the Dojo.

From the scrolls

CREATE: Testing LLMs for Associative Creativity

A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate models' capacity for creative associative reasoning. CREATE requires models to generate sets of paths connecting concepts in a model's parametric knowledge. Paths should have high specificity (distinctiveness and closeness of the concept connection) and high diversity (dissimilarity from other paths), and models are s

cs.CL

Visit arXiv →

Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People

As social virtual reality (VR) grows more popular, addressing accessibility for blind and low vision (BLV) users is increasingly critical. Researchers have proposed an AI "sighted guide" to help users navigate VR and answer their questions, but it has not been studied with users. To address this gap, we developed a large language model (LLM)-powered guide and studied its use with 16 BLV participants in virtual environments with confederates posing as other users. We found that when alone, partic

cs.HCcs.AIcs.ET

Visit arXiv →

Emotional Modulation in Swarm Decision Dynamics

Collective decision-making in biological and human groups often emerges from simple interaction rules that amplify minor differences into consensus. The bee equation, developed initially to describe nest-site selection in honeybee swarms, captures this dynamic through recruitment and inhibition processes. Here, we extend the bee equation into an agent-based model in which emotional valence (positive-negative) and arousal (low-high) act as modulators of interaction rates, effectively altering the

cs.MAcs.AI

Visit arXiv →

BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion

Language-conditioned local navigation requires a robot to infer a nearby traversable target location from its current observation and an open-vocabulary, relational instruction. Existing vision-language spatial grounding methods usually rely on vision-language models (VLMs) to reason in image space, producing 2D predictions tied to visible pixels. As a result, they struggle to infer target locations in occluded regions, typically caused by furniture or moving humans. To address this issue, we pr

cs.ROcs.AIcs.CV

Visit arXiv →

Think Before You Lie: How Reasoning Improves Honesty

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral trade-offs where honesty incurs variable costs. Contrary to humans, who tend to become less honest given time to deliberate (Capraro, 2017; Capraro et al., 2019), we find that reasoning consistently increases honesty across scales and for several LLM families.

cs.AIcs.CLcs.LG

Visit arXiv →

Towards a Neural Debugger for Python

Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them into neural interpreters (FAIR CodeGen Team et al., 2025). However, developers rarely execute programs step by step; instead, they use debuggers to stop execution at certain breakpoints and step through relevant portions only while inspecting or modifying program variables. Existing neural interpreter

cs.LGcs.AIcs.SE

Visit arXiv →

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

Deep Reinforcement Learning systems are highly sensitive to the learning rate (LR), and selecting stable and performant training runs often requires extensive hyperparameter search. In Proximal Policy Optimization (PPO) actor--critic methods, small LR values lead to slow convergence, whereas large LR values may induce instability or collapse. We analyse this phenomenon from the behavior of the hidden neurons in the network using the Overfitting-Underfitting Indicator (OUI), a metric that quantif

cs.LGcs.AI

Visit arXiv →

The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?

Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when it fails. The formal conditions are simple: rank-alignment and no inversion zones. The substantive contribution is identifying why these conditions hold or fail: the distinction between structural uncertainty (missing data, e.g., cold-start) and contextual un

cs.AI

Visit arXiv →

PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs

Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading criteria, and clinical evidence. In practice, diagnostic reasoning requires linking morphological evidence with formal diagnostic and grading criteria. Although multimodal large language models (MLLMs) demonstrate strong vision language reasoning capabilities, they lack explicit mechanisms for structured knowledge integration and interpretable memory

cs.AI

Visit arXiv →

Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand

In the diverse landscape of 6G networks, where wireless connectivity demands surge and spectrum resources remain limited, flexible spectrum access becomes paramount. The success of crafting such schemes hinges on our ability to accurately characterize spectrum demand patterns across space and time. This paper presents a data-driven methodology for estimating spectrum demand variations over space and identifying key drivers of these variations in the mobile broadband landscape. By leveraging geos

eess.SYcs.AIcs.NI

Visit arXiv →

What the masters say

@GoogleDeepMind @FryRsquared + the newest @GoogleDeepMind Podcast is all about AlphaGo! Check it out here: https://t.co/KlmDKbmNR9

@demishassabis

And if you want even more AlphaGo + AI for Science content, there’s a recent episode of the @GoogleDeepMind Podcast with the awesome @FryRsquared and I discussing the Alpha series + AGI amongst many other things! https://t.co/u3QyJVfoHs

@demishassabis

If you're interested in a behind-the-scenes look at the full match and story, watch the award-winning AlphaGo documentary: https://t.co/DkDU3q4HVn

@demishassabis

Read about AlphaGo’s incredible impact over the past 10 years and our vision for the future: https://t.co/utLIKwSGqg

@demishassabis

Ten years ago, AlphaGo’s legendary match in Seoul heralded the start of the modern era in AI. Its famous ‘Move 37’ signaled to us that AI techniques were ready to tackle real-world problems in areas like science - and ideas inspired by these methods are critical to building AGI h

@demishassabis

to me personally, this continues the years of close partnership with NVIDIA I've had via @PyTorch. working with them is always such a joy!

@soumithchintala

Excited to partner with NVIDIA. bringing up 1GW or more of compute starting with Vera Rubin, co-designing systems and architectures together, and more. NVIDIA has also made a significant investment in @thinkymachines https://t.co/cgmnhfA4qM

@soumithchintala

3rd edition 日本語版が好評発売中！是非お近くの本屋さんにてお手に取って頂けたら幸いです https://t.co/7YTN5FrHmq

@fchollet

@GoogleDeepMind @FryRsquared + the newest @GoogleDeepMind Podcast is all about AlphaGo! Check it out here: https://t.co/KlmDKbmNR9

@demishassabis

If you're interested in a behind-the-scenes look at the full match and story, watch the award-winning AlphaGo documentary: https://t.co/DkDU3q4HVn

@demishassabis

Read about AlphaGo’s incredible impact over the past 10 years and our vision for the future: https://t.co/utLIKwSGqg

@demishassabis

to me personally, this continues the years of close partnership with NVIDIA I've had via @PyTorch. working with them is always such a joy!

@soumithchintala

3rd edition 日本語版が好評発売中！是非お近くの本屋さんにてお手に取って頂けたら幸いです https://t.co/7YTN5FrHmq

@fchollet

Updated 3/11/2026, 1:14:52 PM

Go Touch Some Grass

From the scrolls

CREATE: Testing LLMs for Associative Creativity

Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People

Emotional Modulation in Swarm Decision Dynamics

BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion

Think Before You Lie: How Reasoning Improves Honesty

Towards a Neural Debugger for Python

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?

PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs

Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand

What the masters say

Hacker News

Create value for others and don’t worry about the returns

I'm going to build my own OpenClaw, with blackjack and bun

Zig – Type Resolution Redesign and Language Changes

U+237C ⍼ Is Azimuth

Cloudflare crawl endpoint

Julia Snail – An Emacs Development Environment for Julia Like Clojure's Cider

AutoKernel: Autoresearch for GPU Kernels

Tony Hoare has died

Agents that run while I sleep

Yann LeCun raises $1B to build AI that understands the physical world

Create value for others and don’t worry about the returns

I'm going to build my own OpenClaw, with blackjack and bun

Zig – Type Resolution Redesign and Language Changes

U+237C ⍼ Is Azimuth

Cloudflare crawl endpoint

Julia Snail – An Emacs Development Environment for Julia Like Clojure's Cider

AutoKernel: Autoresearch for GPU Kernels

Tony Hoare has died

Agents that run while I sleep

Yann LeCun raises $1B to build AI that understands the physical world