AI/ML arXiv cs.AI

tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration

Presentation of tap, a file-based protocol enabling heterogeneous LLM agents from different vendors to collaborate on shared codebases.

AI/ML arXiv cs.AI

MoDiCoL: A Modular Diagnostic Continual Learning Dataset for Robust Speech Recognition

MoDiCoL, a modular diagnostic dataset for continual learning in speech recognition, designed to improve robustness against real-world shifts.

AI/ML arXiv cs.AI

The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

Research demonstrating that explanations in audio deepfake detection models can be manipulated via psychoacoustic perturbations without changing predictions.

AI/ML arXiv cs.AI

A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction

HamEvo, a neural operator for predicting the Kohn-Sham Hamiltonian, offering significantly faster inference than conventional DFT.

AI/ML arXiv cs.AI

Fodor and Pylyshyn's Systematicity Challenge Still Stands

A critical analysis arguing that the challenge of systematicity in human cognition remains unsolved by current neural network architectures.

Other Hacker News

Techno-libertarians are flocking to the Caribbean

A discussion regarding techno-libertarians moving to the Caribbean to establish sovereign zones or escape government regulation.

Other Hacker News

The Dead Economy Theory

An exploration of the 'Dead Economy Theory', likely discussing economic stagnation or systemic failure through a theoretical lens.

Software Engineering Hacker News

What job interviews taught me about Kubernetes

A personal reflection on the nature of Kubernetes job interviews and what they reveal about the industry's perception of the tool.

Tech Business/VC TechCrunch

The US government’s Anthropic models ban was never about an AI jailbreak

An analysis of the US government's ban on specific Anthropic AI models, highlighting government interference in the AI industry.

AI/ML arXiv cs.AI

PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-Space Continuum

Introduces PLAIground, a framework for SLO-driven runtime model selection in Compound AI systems across edge, cloud, and space environments.

AI/ML arXiv cs.AI

No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements

Proposes 'agent-first canonical code' to reduce human code entropy and potentially lower frontier model requirements for coding tasks.

AI/ML arXiv cs.AI

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

Presents Elastic Queries Reinforcement Learning (EQRL) to make VLA model inference and replanning schedules elastic based on state difficulty.

AI/ML arXiv cs.AI

Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks

Develops a geometric theory of discovery bottlenecks to determine when LLM-guided non-local exploration is effective in scientific discovery.

AI/ML arXiv cs.AI

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR

Investigates continual learning for ASR systems to better handle disfluent speech without losing general-domain knowledge.

AI/ML arXiv cs.AI

Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

Reports on Hy-Embodied-0.5-VLA (HyVLA-0.5), an end-to-end robot learning stack covering data collection through real-world deployment.

Software Engineering Hacker News

A calculator that doesn't round

Discussion regarding a calculator implementation designed to avoid rounding errors, focusing on precision and mathematical correctness.

AI/ML Hacker News

Show HN: Vet turned founder, AI lawn diagnosis

A founder and veteran has created an AI-powered tool for diagnosing lawn health issues.

AI/ML The Verge

Facebook’s new AI Mode search gets its info from public posts

Meta is introducing an 'AI Mode' for Facebook search that utilizes public posts to generate AI-driven results.

Tech Business/VC The Verge

Xbox is closing down Hellblade creator Ninja Theory

Xbox is reportedly closing Ninja Theory and negotiating spin-offs for other studios as part of a business 'reset'.

Other Ars Technica

COVID vaccines still protect against heart problems, large study finds

A large study indicates that COVID vaccines continue to provide protection against heart problems.