Hardware/Chips Hacker News

Popping the GPU Bubble

A community discussion on Hacker News regarding the potential economic bubble surrounding GPU demand and infrastructure.

Other Hacker News

Study suggests most Americans would be healthier without daylight saving time

A study suggesting that Americans would be healthier if daylight saving time were abolished.

AI/ML VentureBeat

Meituan open sources LongCat-2.0, the 1.6T, near-frontier agentic coding model that's been leading OpenRouter — trained entirely on Chinese chips

Meituan open sources LongCat-2.0, a 1.6T parameter MoE coding model trained on Chinese ASICs, featuring a 1M token context window and MIT license.

AI/ML arXiv cs.AI

Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring

Research on preventing error propagation in multi-agent AI systems through runtime monitoring and reasoning exchange.

Cybersecurity arXiv cs.AI

Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering

A study exploring how memory in LLM agents can be used as an attack surface to manipulate model outputs.

AI/ML arXiv cs.AI

Low-cost concept-based localized explanations: How far can we get with training-free approaches?

An evaluation of training-free, zero-shot approaches for localized concept naming in Explainable AI using MLLMs.

AI/ML arXiv cs.AI

Managing the Human Fallback: Skill Investment Under Improving AI and Worker Mobility

An economic model analyzing the balance of human skill investment and AI deployment within firms.

AI/ML arXiv cs.AI

Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem

An empirical study of over 6,000 n8n workflows to characterize the design and reliability of LLM agentic workflows in low-code platforms.

AI/ML arXiv cs.AI

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

Introduction of HiComm, a hierarchical communication module for Multi-agent Reinforcement Learning that reduces communication volume.

AI/ML arXiv cs.AI

Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement

Introduction of Flow Reasoning Models (FRMs) that use iterative self-refinement and test-time scaling to solve structured reasoning tasks.

Other Hacker News

A Fake Shell for Pangenomics

A discussion or tool related to a fake shell environment designed for pangenomics research.

AI/ML arXiv cs.AI

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Researchers introduce 'Agentic Abstention' and the CONVOLVE context engineering method to help LLM agents recognize when to stop acting to avoid unnecessary tool calls.

AI/ML arXiv cs.AI

Agent Safety Is Action Alignment

The paper argues that agent safety should be enforced as 'least privilege' outside the model at the action boundary rather than relying on in-weight refusal training.

AI/ML arXiv cs.AI

Self-Supervised Theorem Discovery in a Formal Axiomatic System

An agent is developed that can autonomously discover useful mathematical theorems from axioms alone via a self-supervised algorithm without human priors.

AI/ML arXiv cs.AI

Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

A mechanistic interpretability approach uses sparse autoencoders to identify and steer personality traits in LLMs via latent feature interventions.

AI/ML arXiv cs.AI

HyphaeDB: A Living Knowledge Topology for Agent-First Memory

HyphaeDB is introduced as an agent-native memory infrastructure that uses HNSW graph topology and gossip protocols for multi-agent knowledge propagation.

AI/ML arXiv cs.AI

Primary ICD Category Prediction using LLM-based Probing

A study demonstrates that frozen medical LLM representations can effectively unify structured and narrative EHR data for primary ICD category prediction.

AI/ML arXiv cs.AI

MedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes

MedEvoEval is a new longitudinal evaluation framework for assessing how 'doctor agents' evolve and improve through simulated clinical episodes.

AI/ML arXiv cs.AI

Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries

Physician-led evaluation shows that specialized clinical AI tools outperform general-purpose frontier models on real-world point-of-care queries.

AI/ML arXiv cs.AI

Customized Generative AI Agent for Transportation Engineering Practice: A Development and Continued Pre-training Guideline

A guideline is proposed for developing transportation engineering AI agents using continued pre-training with LoRA on domain-specific manuals.