Ax Kevin H. Guo, Chao Yan, Avinash Baidya, Katherine Brown, Xiang Gao, Juming Xiong, Zhijun Yin, Bradley A. Malin 22d ago

Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Diagnostic Reasoning

Evaluation of 17 LLMs showing diagnostic reasoning degrades across multi-turn conversations compared to single-turn benchmarks.

Ax Xiangyu Zeng, Qi Xu, Yunke Wang, Chang Xu 22d ago

HiCI: Hierarchical Construction-Integration for Long-Context Attention

HiCI: Hierarchical attention module for long-context language modeling, organizing information from local to global levels.

Ax Amuche Ibenegbu, Pierre Lafaye de Micheaux, Rohitash Chandra 22d ago

tBayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data

tBayes-MICE: Bayesian approach to multiple imputation for time-series data with missing values via MCMC sampling.

Ax Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, Dmitrii Ustiugov 22d ago

CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference

CodecSight optimizes streaming vision-language model inference by leveraging video codec signals for end-to-end efficiency.

Ax Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, JinYeong Bak 22d ago

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

DOVE benchmark for evaluating LLM cultural value alignment using open-ended generation, addressing limitations of multiple-choice formats.

Ax Youssef Abdou 22d ago

The Unreasonable Effectiveness of Data for Recommender Systems

Study investigating saturation points in recommender system performance as training dataset size increases, with reproducible Python implementation.

Ax Asmaa Eldesoukey, Yongxin Chen, Abhishek Halder 22d ago

A Generalized Sinkhorn Algorithm for Mean-Field Schr\"odinger Bridge

Theoretical work on Schrödinger bridge problem with mean-field dynamics for multi-agent systems control.

Ax Hanyang Wang, Mingxuan Zhu 22d ago

The Detection-Extraction Gap: Models Know the Answer Before They Can Say It

Research: Chain-of-thought models generate 52-88% of tokens after answers are already recoverable, revealing inefficiency in reasoning.

Ax Yanan Cao, Ashish Ranjan, Sinduja Subramaniam, Evren Korpeoglu, Kaushiki Nag, Kannan Achan 22d ago

CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation

ML research on cadence-aware encoding for next-basket recommendation in retail, modeling repurchase timing patterns.

HN chirsz 22d ago

JSON with Commas and Comments

JSON extension format supporting trailing commas and comments. Minor format specification unrelated to AI.

HN kotobuki 22d ago

Some LLM routers are injecting malicious tool calls

Brief mention of LLM routers injecting malicious tool calls as security issue. Insufficient detail.

HN omegaproto 22d ago

.

Bittensor governance controversy and token price impact.

HN stjuan627 22d ago

A few thoughs about AI videos

Personal experience report on using AI video generation models. Notes Gemini Nano, Veo3, Sora2, and Chinese models. Anecdotal observations.

HN obilgic 22d ago

Next SaaS replacement is an agent with a dashboard – kern

Analysis of AI agents as SaaS replacement with integrated database, logic, and UI.

HN vamshidhar199 22d ago

Show HN: Ctxlint – Lint your AGENTS.md for stale refs and token waste

Linter tool for AI agent context files and MCP configs. Detects stale references, token waste, hardcoded secrets. Cites research on context bloat reducing agent performance.

HN rmason 22d ago

Multica the open-source managed agents platform

Open-source platform for managing AI coding agents as teammates. Agents autonomously handle task assignment, code writing, and progress tracking without prompt copying.

HN john1203 22d ago

Claude, What a Marketing Sham

User complaint about Claude signup experience and support quality. Opinion-based critique without technical depth.

HN gmays 22d ago

ActionParty: Multi-Subject Action Binding in Generative Video Games

Research on video generation models struggling with multi-subject action binding. Introduces ActionParty with per-subject state tokens to improve action accuracy.

HN 1vuio0pswjnm7 22d ago

Google's AI Overviews spew false answers per hour, bombshell study reveals

Study reports Google's Gemini models generate inaccurate search results 9-15% of the time across 8,652 queries. Evaluates LLM reliability in production systems.

HN rmason 22d ago

xAI sues Colorado over first state AI anti-discrimination law

xAI lawsuit against Colorado AI anti-discrimination law. Legal/regulatory news without technical substance.

HN rpst 22d ago

Show HN: Facebook Marketplace MCP

Facebook Marketplace MCP integration allowing Claude to search and monitor deals via command line. Demonstrates AI agent tool use.

HN aanet 22d ago

Black Forest Labs – The 70-Person AI Image Startup Taking on Silicon Valley

Profile of Black Forest Labs, 70-person German AI image startup competing in image generation. Business/market focus, minimal technical substance.

HN VectorVault 22d ago

How are you governing token spend and data exposure in prod AI agent loops?

Discussion question about managing token costs and data exposure in production AI agent systems. Operational concern without detailed analysis.

HN matt_d 22d ago

Agentic Code Optimization via Compiler-LLM Cooperation

arXiv framework page for collaborative feature development. No technical content about the claimed compiler-LLM optimization research.

HN possumously 22d ago

Tend: Lightweight attention infrastructure for humans and AI agents

Tend: lightweight infrastructure for managing multiple concurrent AI agents and projects. Handles agent coordination, context switching, and multi-project workflows.

HN 120bits 22d ago

Ask HN: Looking for AI Video Upscaler

Forum question asking for AI video upscaling tool recommendations. No technical depth or research.

HN sagari 22d ago

5 LLM played Poker: Opus busted first, Grok won

Five LLM-based agents play Texas Hold'em with distinct personalities and reasoning styles.

HN Bender 22d ago

Police corporal created AI porn from driver's license pics

News report about police misuse of AI for non-consensual deepfakes. No technical or research relevance.

HN signa11 22d ago

The role of LLMs in patch review

Discussion of LLM application to code patch review. Limited content, but relevant to developer tools and LLM applications.

HN chtefi 22d ago

Stream your terminal. Watch AI agents work. Like Twitch, for shells

Tool for streaming terminal activity to observe AI agent execution. Visualization/monitoring for agent workflows.

HN theaniketmaurya 22d ago

Show HN: SmolVM – open-source sandbox for coding and computer-use agents

Open-source local sandbox environment for AI agents on macOS/Linux. SDK/CLI enables persistent state, file I/O, pause/resume, and desktop environment interaction for agent workflows.

BL 22d ago

Using projects in ChatGPT

Announcement of AI Dev 26 conference in San Francisco with no technical details provided.

BL 22d ago

Prompting fundamentals

Tutorial on writing effective prompts for ChatGPT to improve response quality.

BL 22d ago

Analyzing data with ChatGPT

Tutorial on using ChatGPT for data analysis, visualization, and insight generation.

BL 22d ago

Creating images with ChatGPT

Image generation with ChatGPT: creating and refining original images from text prompts and iterating variations.

BL 22d ago

ChatGPT for marketing teams

ChatGPT for marketing: campaign planning, content creation, variation generation, and performance analysis.

BL 22d ago

AI fundamentals

Introduction to AI fundamentals: definitions, capabilities, and how AI systems work for non-technical audiences.

BL 22d ago

Writing with ChatGPT

Using ChatGPT for workplace writing: drafting, revising, tone adjustment, and refining communication.

BL 22d ago

ChatGPT for customer success teams

ChatGPT for customer success: account management, communication, onboarding, and coordination.

BL 22d ago

Healthcare

AI resources for clinical workflows: evidence search, guideline reconciliation, and documentation support in healthcare.

BL 22d ago

Financial services

Resources for evaluating, deploying, and scaling AI in regulated financial services environments.

BL 22d ago

Brainstorming with ChatGPT

Using ChatGPT as a brainstorming partner to generate ideas, organize thinking, and create actionable plans.

BL 22d ago

ChatGPT for operations teams

ChatGPT for operations: turning fragmented inputs into summaries, SOPs, and operational updates.

BL 22d ago

ChatGPT for managers

ChatGPT for managers: preparation, team coordination, notes organization, and communication.

BL 22d ago

Personalizing ChatGPT

Personalizing ChatGPT behavior with instructions and memory for consistent, customized outputs.

BL 22d ago

Responsible and safe use of AI

Best practices for safe and responsible use of ChatGPT and LLMs in knowledge work.

BL 22d ago

Working with files in ChatGPT

ChatGPT file handling: uploading and working with spreadsheets, documents, PDFs, and images in conversations.

BL 22d ago

Getting started with ChatGPT

Basic tutorial on getting started with ChatGPT and conversational AI fundamentals.

BL 22d ago

Research with ChatGPT

Using ChatGPT's search and deep research features to find, analyze, and synthesize information from the web.

BL 22d ago

ChatGPT for sales teams

ChatGPT applications for sales teams: research, prep, follow-up, and deal coordination.