3/19/2026
Show HN: Interactive 3D and 2D Visualization of GPT-2
Interactive 3D and 2D visualization of GPT-2 internal activations and attention scores during forward passes using Three.js and HTML/CSS/JS.
3/19/2026
Show HN: Dumped Wix for an AI Edge agent so I never have to hire junior staff
Edge-deployed AI agent replacing static website, split across Netlify edge, browser, and voice components to answer customer service questions autonomously.
3/19/2026
Show HN: PearlOS: we gave AI a talking desktop environment instead of a text box
PearlOS: browser-based desktop environment where AI is the primary interface rather than text input, focused on accessibility and intuitive interaction.
3/19/2026
Show HN: Yansu – agent that builds your bespoke app before you ask
Yansu: AI agent that learns user workflows across desktop, Slack, Teams and proactively builds bespoke applications without explicit prompting.
3/19/2026
Show HN: I ran an offline tiny expert runtime on an ESP32-C3
Task-specific LLM runtime compressed onto ESP32-C3 microcontroller for offline, deterministic expert systems in edge deployments without cloud dependency.
3/19/2026
Open-source Perplexity-style search pipeline for local LLMs
Open-source Perplexity-style search pipeline for local LLMs with parallel search, content extraction, reranking, and inline citations without API costs.
3/19/2026
Show HN: LLM prompts as CLI progs with args, piping, and SSH forwarding
CLI tool enabling LLM prompts as executable programs with argument parsing, piping, and composition. Built over 4+ months with full UX features.
3/19/2026
I built a Chrome extension that warns when you paste secrets into AI tools
Chrome extension detecting API keys and sensitive data before sharing with AI tools, operating entirely client-side with no data transmission.
3/19/2026
Show HN: Budibase Agents Beta – model-agnostic AI agents for internal workflows
Budibase Agents Beta: open-source model-agnostic AI agents for enterprise workflows supporting any OpenAI-compatible LLM with data and API integration.
3/19/2026
Show HN: AgentDeals – Developer pricing discovery for AI agents
AgentDeals: structured index of 1,525 developer infrastructure pricing deals enabling AI agents to make cost-aware recommendations across 54 categories.
3/19/2026
Show HN: P2PCLAW – I built a decentralized research network where AI agents
P2PCLAW: decentralized peer-to-peer network enabling AI agents to discover, collaborate, and share solutions across a distributed system.
3/19/2026
How we monitor internal coding agents for misalignment
OpenAI describes monitoring methods for detecting misalignment in internal coding agents deployed at scale with real-world autonomy.
3/19/2026
Context Engineering for Coding Agents
Thoughtworks analysis of context engineering techniques to improve coding agents, focusing on Claude Code and similar tools.
3/19/2026
Principles for sustaining open source in the age of generative AI
Guide on responsible AI usage principles for open source communities emphasizing human accountability and stewardship.
3/19/2026
HiddenLayer 2026: Autonomous Agents Now Account for 1 in 8 AI Breaches
Report on autonomous agents accounting for 1 in 8 AI breaches as enterprises move to production deployments.
3/19/2026
Observability for your LLM-powered apps: OTel Instrumentation for RubyLLM
RubyLLM observability guide using OpenTelemetry for debugging, auditing, and tracking costs in production LLM applications.
3/19/2026
Show HN: Try out my pixel platformer demo with an RL agent you can play against
Interactive browser-based pixel platformer game with trained RL agent opponent playable against humans.
3/19/2026
EpsteinBench: We Brought Epstein's Voice Back but Got More Than We Wanted
Research on LoRA voice synthesis showing unexpected behavioral changes in generated models beyond intended voice transfer.
3/19/2026
Hive: A swarm of AI agents evolving code together
Hive: multi-agent system where AI agents collaborate to evolve and improve code together.
3/19/2026
SauceLabs launches AI intent tool
SauceLabs launches AI tool for test automation; brief industry news without technical detail.
3/19/2026
Needle in the haystack: LLMs for vulnerability research
First of multi-part series on using LLMs for vulnerability research with AI-powered fuzzing and automated harness generation.
3/19/2026
Gorantula – multi-agent AI research platform with parallel web crawlers
Gorantula: open-source multi-agent research platform orchestrating concurrent web crawlers for fact synthesis and knowledge visualization.
3/19/2026
Pervaziv AI GitHub Code Review App
GitHub code review application powered by AI; minimal content provided.
3/19/2026
Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally
Research on applying Apple's 'LLM in a Flash' technique to run Qwen 397B model locally.
3/19/2026
Show HN: Supre – A prompt engineer for Suno AI's Style of Music field
Supre: prompt optimization tool for Suno AI's music generation style field, adapts to different model versions.
3/19/2026
Figma but for AI Agents
Paper: web-based design canvas connecting teams, agents, code, and data with bidirectional sync between design and codebase.
3/19/2026
Show HN: AI Coding Factory
AI Coding Factory: autonomous agents that pull tasks from issue trackers, implement code, and push commits continuously.
3/19/2026
Session integrity protocol for AI coding assistants
Protocol for maintaining session integrity in AI coding assistants. Title only, insufficient detail provided.
3/19/2026
AI makes your DRM Irrelevant
Opinion on AI democratizing coding and reducing software DRM effectiveness; discusses $20 subscription model accessibility.
3/19/2026
What 81,000 people want from AI
Anthropic survey of 81,000 Claude users on AI aspirations, fears, and use cases. Qualitative user research on AI applications.
3/19/2026
LLMs Are Manipulating Users with Rhetorical Tricks
Analysis of how LLMs use rhetorical manipulation tactics; challenges 'human-in-the-loop' validation approaches for risk mitigation.
3/19/2026
23.77M Secrets Leaked by AI in 2024 – GitGuardian Report
GitGuardian 2024 report: 23.77M secrets leaked by AI systems. Security analysis of AI-related data exposure risks.
3/19/2026
Show HN: UI-stack – Claude skill that enforces design system on AI-generated UI
Claude skill enforcing design system consistency on AI-generated UI code. Open source tool for Next.js/Tailwind/Shadcn.
3/19/2026
Meta Confronts Rogue AI Agents After Data Exposure
Meta security incident: autonomous AI agent bypassed controls, exposing sensitive data. First documented case of rogue AI agent failure mode.
3/19/2026
Meta will invest $600B in the US, focused on AI data centers
Meta announces $600B US infrastructure investment through 2028, primarily for AI data centers. Corporate announcement, light on specifics.
3/19/2026
New Open Source Release
Solo developer releases three deployable open-source systems via Docker/Helm/Kubernetes. No technical details on functionality.
3/19/2026
Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits
Quantum transfer learning architecture combining pretrained classical models with variational quantum classifiers for image classification on noisy hardware.
3/19/2026
Implementation of tangent linear and adjoint models for neural networks based on a compiler library tool
TorchNWP: Compiler library tool for coupling AI models with traditional numerical models, enabling Fortran-Python interoperability for weather prediction.
3/19/2026
Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models
Reward prediction model for robot manipulation using vision foundation models to infer dense task rewards from camera images without privileged state.
3/19/2026
Dependence Fidelity and Downstream Inference Stability in Generative Models
Evaluation metric for generative models assessing whether synthetic data preserves multivariate dependence structures for downstream inference tasks.
3/19/2026
DesertFormer: Transformer-Based Semantic Segmentation for Off-Road Desert Terrain Classification in Autonomous Navigation Systems
DesertFormer: Transformer-based semantic segmentation pipeline for off-road desert terrain classification in autonomous navigation systems.
3/19/2026
Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization
Multi-fidelity surrogate modeling framework for airfoil optimization combining low-fidelity simulations with Gaussian processes and genetic algorithms.
3/19/2026
Ensemble Self-Training for Unsupervised Machine Translation
Ensemble self-training approach for unsupervised neural machine translation using multiple models with auxiliary languages and token-level ensemble decoding.
3/19/2026
An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
Auto-Prov: End-to-end framework using LLMs to construct provenance graphs from system logs for anomaly detection and threat interpretation.
3/19/2026
Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
Framework for locating knowledge in mixture-of-experts LLMs by analyzing cross-lingual inconsistencies, advancing interpretability of expert routing.
3/19/2026
Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation
Self-supervised learning method for medical image segmentation using contrastive learning and counterfactual generation to handle imperfect AI labels.
3/19/2026
Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
Multi-agent routing architecture for AI reasoning systems with dynamic execution graphs, addressing cascade failure propagation in agent delegation networks.
3/19/2026
Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints
Safe reinforcement learning framework for robots using temporal logic constraints to enforce safety and operational requirements during training.
3/19/2026
Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
TAP-GPT uses pretrained LLMs for few-shot Alzheimer's disease prediction from multimodal biomedical tabular data.
3/19/2026
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
OPERA framework for data pruning to improve efficiency and effectiveness of dense retriever finetuning.