3/24/2026
Helping developers build safer AI experiences for teens
OpenAI releases open-weight safety model gpt-oss-safeguard and prompt-based policies for teen-safe AI applications.
3/24/2026
Open-Source AI Text-to-Speech Models You Can Run Locally for Natural Voice
Overview of open-source text-to-speech models deployable locally. Compares quality, cost, and control versus cloud APIs.
3/24/2026
AI Agents Can Autonomously Perform Experimental High Energy Physics
Research on using AI agents to autonomously perform high energy physics experiments. Demonstrates autonomous scientific research capabilities.
3/24/2026
LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?
Technical research on LLM internals using layer duplication and probing methods. Discovered RYS method achieving top HuggingFace leaderboard ranking without training.
3/24/2026
Yann LeCun's LeWorldModel: Stable End-to-End JEPA from Pixels
LeWorldModel: Joint Embedding Predictive Architecture for stable end-to-end world model learning from raw pixels without auxiliary supervision.
3/24/2026
Review AI agent changes locally before you push
Tool for reviewing AI coding agent changes locally before pushing, solving code review bottleneck with PR-like workflows.
3/24/2026
We almost bought an automation platform. Cowork was one
Case study of evaluating Cowork automation platform alongside Claude Enterprise for employee productivity integration with business tools.
3/24/2026
Powering product discovery in ChatGPT
ChatGPT shopping assistant using Agentic Commerce Protocol for product discovery and comparison.
3/24/2026
Modular 26.2: Image Generation and Upgraded AI Coding with Mojo
Modular 26.2 release adds image generation/editing workflows and improves Mojo for GPU kernel AI development.
3/24/2026
Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build
ProofShot: CLI tool enabling AI coding agents to view browser output, capture screenshots/video/errors for verification during UI development.
3/24/2026
Show HN: Kern – One agent. One folder. One mind. Every channel
Kern: AI agent framework maintaining single continuous session across CLI, Telegram, Slack with persistent local memory in plain folder.
3/24/2026
Show HN: Prompts Directory for Data Analyst
Prompt repository with curated templates for data analysts covering exploration, cleaning, SQL, dashboards, and visualization.
3/24/2026
Long-Running Sandbox in Dockers for Coding Agents (100% POSIX Compatible)
Sandock: Docker-based sandbox for running AI coding agents with persistent volumes, POSIX compatibility, cost-effective alternative to VMs.
3/24/2026
Ask HN: System Programming as a LLM shelter
Discussion on whether system programming offers refuge from LLM-assisted development trends due to different performance priorities.
3/24/2026
Ask HN: HSL 0.1 – The Human Source License. Please help refining
Discussion of Human Source License for open source stream processing library built on PyDBSP.
3/24/2026
Expert Personas Improve LLM Alignment but Damage Accuracy
Research showing expert personas improve LLM alignment but reduce accuracy, trade-offs in prompt engineering.
3/24/2026
The 53-Year Evolution of AI Agents: A Comprehensive Reading List
Comprehensive reading list tracing 53-year research lineage of AI agents from 1970s theoretical foundations through modern implementations.
3/24/2026
Show HN: Shard-based scheduling for 100x more fine-tuning experiments on 4 GPUs
Shard-based scheduling system for scaling LLM fine-tuning experiments on limited GPU resources, enabling 100x more experiments on 4 GPUs.
3/24/2026
Financial Benchmarks – Evaling LLMs on Financial Tasks
Benchmark dataset for evaluating LLMs on financial tasks. Minimal content provided but addresses important evaluation gap.
3/24/2026
Pool spare GPU capacity to run LLMs at larger scale
Distributed inference system pooling spare GPU capacity for LLM inference with automatic model distribution via pipeline parallelism and expert sharding.
3/24/2026
MiniMind: End-to-end GPT-style LLM training pipeline in pure PyTorch
MiniMind: End-to-end PyTorch GPT-style LLM training pipeline enabling full model training in 2 hours on single GPU for personal exploration of LLM internals.
3/24/2026
GPT from GPT: de novo microgpt
GPT from GPT: hand-written 200-line GPT implementation in Python demonstrating LLM ability to create microgpt as distilled Transformer essence.
3/24/2026
Model-based linguistic space for transmitting our thoughts from brain to brain
Research on brain-to-brain communication using LLM embeddings to align speaker and listener brain activity during conversations via electrocorticography.
3/24/2026
AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
AgenticGEO: self-evolving agentic system for generative engine optimization using LLMs to maximize content visibility in black-box search engine outputs.
3/24/2026
ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
ProMAS: proactive error forecasting for multi-agent LLM systems using Markov transition dynamics to detect failures in real-time before system-wide propagation.
3/24/2026
Domain-Specialized Tree of Thought through Plug-and-Play Predictors
DST framework: domain-specialized Tree of Thought using plug-and-play predictors for efficient branch pruning, balancing exploration depth and computational cost.
3/24/2026
FactorSmith: Agentic Simulation Generation via Markov Decision Process Decomposition with Planner-Designer-Critic Refinement
FactorSmith: agentic framework generating executable game simulations from natural language using LLMs with factored POMDP decomposition and planner-designer-critic refinement.
3/24/2026
Me, Myself, and $\pi$ : Evaluating and Explaining LLM Introspection
arXiv paper proposing taxonomy to evaluate genuine introspection and meta-cognition in LLMs, distinguishing self-reflection from text-based pattern matching.
3/24/2026
AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse
AgentComm-Bench: benchmark suite stress-testing cooperative multi-agent embodied AI systems under realistic network conditions including latency, packet loss, and bandwidth constraints.
3/24/2026
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
arXiv paper on LLM-enhanced contrastive learning for detecting out-of-distribution data in text-attributed graphs with applications to citation and social networks.
3/24/2026
Leveraging Natural Language Processing and Machine Learning for Evidence-Based Food Security Policy Decision-Making in Data-Scarce Making
ZeroHungerAI: NLP and ML framework for food security policy modeling in data-scarce regions using structured socio-economic data and textual reports.
3/24/2026
Deep reflective reasoning in interdependence constrained structured data extraction from clinical notes for digital health
LLM agent framework using iterative self-critique and revision to extract structured data from clinical notes while respecting interdependent variable constraints.
3/24/2026
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
DiffGraph: Agent-driven framework for merging multiple text-to-image diffusion models using graph-based approach to better leverage expert models for diverse generation tasks.
3/24/2026
Efficient Counterfactual Reasoning in ProbLog via Single World Intervention Programs
Single World Intervention Programs approach for efficient counterfactual reasoning in ProbLog enabling interpretable what-if analysis.
3/24/2026
Grounded Chess Reasoning in Language Models via Master Distillation
Framework distilling expert chess reasoning into natural language chain-of-thought explanations enabling compact models to acquire domain expertise.
3/24/2026
LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
LLM-driven framework synthesizing interpretable human-readable Python controllers for hot steel rolling by iteratively refining heuristics with simulator feedback.
3/24/2026
Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems
Proposes Context Cartography framework for structured governance of contextual space in LLM systems addressing lost-in-middle and long-distance degradation.
3/24/2026
Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI
Position paper on multi-agent systems in healthcare requiring contestability mechanisms beyond explainability for trustworthy collective decision-making.
3/24/2026
Seed1.8 Model Card: Towards Generalized Real-World Agency
Foundation model supporting generalized real-world agency with multi-turn interaction, tool use, code execution, GUI interaction, and configurable inference modes.
3/24/2026
Agentic AI and the next intelligence explosion
Discusses how frontier reasoning models implement internal multi-agent debate systems rather than simple serial thinking for complex problem solving.
3/24/2026
From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
Practical framework for localizing graduate-level AI tutors with minimal resources using Vision-Language Model data cleaning and Shadow-RAG architecture.
3/24/2026
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
Mechanistic interpretability study of vision-language model attention heads and their functional roles in spatial reasoning using CogVSR dataset.
3/24/2026
Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models
Knowledge graph-driven multi-agent framework using LLMs for semantic geospatial data discovery across distributed heterogeneous data ecosystems.
3/24/2026
Modeling Epistemic Uncertainty in Social Perception via Rashomon Set Agents
LLM-driven multi-agent framework modeling epistemic uncertainty in social perception via Rashomon sets in classroom social networks.
3/24/2026
GMPilot: An Expert AI Agent For FDA cGMP Compliance
Domain-specific AI agent for FDA cGMP pharmaceutical compliance using RAG and ReAct frameworks with curated regulatory knowledge base.
3/24/2026
Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems
Presents governance-aware vector subscriptions system for multi-agent knowledge ecosystems that enforces data handling policies in semantic publish-subscribe systems.
3/24/2026
ReLaMix: Residual Latency-Aware Mixing for Delay-Robust Financial Time-Series Forecasting
Introduces ReLaMix for financial time-series forecasting under latency conditions using residual latency-aware mixing to handle delayed observations.
3/24/2026
Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues
Evaluates whether LLM-driven agents in social media simulations exhibit genuine engagement mechanisms by testing information load, descriptive norms, and popularity cues effects.
3/24/2026
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
Proposes profit-driven red teaming framework to stress-test AI agents against adaptive adversarial strategies that manipulate external inputs like retrieved content and tool outputs.
3/24/2026
AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation
Open-source AutoMOOSE framework orchestrates multiphysics simulation lifecycle via agentic AI, coordinating parameter sweeps and diagnosing failures from natural-language prompts.