3/20/2026
TI-89 Height-Mapped Raycaster
Custom raycasting engine for TI-89 calculator with procedurally generated dungeons and 3D rendering on limited hardware.
3/20/2026
LiteParse: Local document parsing for AI agents (Open source)
Open source local document parsing library designed for AI agents.
3/20/2026
Plotra – A digital proof of life for autonomous AI agents
Platform for autonomous AI agents to create and display digital identities on a shared grid.
3/20/2026
Show HN: I built a distributed file store on top of AWS CloudShell
Distributed file store built on AWS CloudShell using Reed-Solomon erasure coding, AES-256-GCM encryption, and regional sharding for resilient storage.
3/20/2026
Age Verification Status of Open Source Operating Systems
Tracker of open source operating systems' compliance status with age verification laws passed or proposed in various US states and Brazil.
3/20/2026
Ask HN: Are we close to figuring out LLM/Agent Memory
Discussion of LLM/agent memory limitations and whether RAG/embeddings or local markdown files are more effective. Community exploration of context retention in agents.
3/20/2026
GopherHole – A universal hub for AI agent-to-agent communication
GopherHole: open protocol for agent-to-agent communication across frameworks. Built-in memory, search, specialized agents. WebSocket-based, privacy-preserving.
3/20/2026
FreeAgent – 60-tool local AI agent, no API keys, no cloud, no cost
FreeAgent: local-first AI agent with 60+ tools (image generation, OSINT, cybersecurity, automation). Runs entirely offline, no cloud dependency or subscriptions.
3/20/2026
I built agents to predict when splitting your AI prompts helps and when it hurts
Analysis of when splitting AI prompts into subagents helps vs hurts output quality. Cognitive science perspective on prompt engineering and agent decomposition.
3/20/2026
Mediahaus suspends senior journalist for using fabricated quotes produced by AI
Journalist suspended for using AI-generated fabricated quotes in published article. Ethics and media accountability issue.
3/20/2026
Taskybear: AI Agent to manage your daily plans
Taskybear: AI agent for daily task and plan management. Limited information provided.
3/20/2026
Benchmarking LLMs/VLMs on document parsing, extraction, VQA
Intelligent Document Processing Leaderboard benchmarks 16+ LLMs/VLMs on document parsing, table extraction, OCR, and visual QA using 9,000+ real documents.
3/20/2026
An AI FAQ for Ordinary People
General FAQ about AI for non-technical audience. Overview of chatbots, image generation, and industrial AI applications.
3/20/2026
GlassWorm malware hits 400 code repos on GitHub, NPM, VSCode, OpenVSX
GlassWorm supply-chain malware campaign compromised 433 packages across GitHub, npm, and VSCode extensions; coordinated attack identified by security researchers.
3/20/2026
Signal's Creator [Moxie Marlinspike] Is Helping Encrypt Meta AI
Signal creator Moxie Marlinspike's Confer platform incorporating encryption into Meta AI systems. Privacy-focused AI infrastructure.
3/20/2026
Google Working on Native Gemini AI App for Mac
Google developing native Gemini AI app for Mac to compete with ChatGPT and Claude dedicated apps.
3/20/2026
Show HN: ContextD – OCRs your screen activity, use it with LLMs via local API
ContextD: macOS app that OCRs screen activity, summarizes with LLM, exposes context via local API. All data stays on device, ~$2/day cost.
3/20/2026
Free daily-updated US tariff data in JSON,Section301,active exclusions
Free daily-updated US tariff data from government sources in JSON format with customs duty collections and Section 301 rates.
3/20/2026
Prism MCP – Session Memory and 94% Context Reduction for AI Agents
Prism MCP is a production-grade Model Context Protocol server with persistent session memory, semantic search, and context reduction (94%) for AI agents with enterprise features.
3/20/2026
Powering the agents: Workers AI now runs large models, starting with Kimi K2.5
Cloudflare Workers AI now supports large language models like Kimi K2.5, providing infrastructure primitives (Durable Objects, Workflows, Sandbox) and an Agents SDK for building and deploying AI agents.
3/19/2026
I wiped a QA database with an AI agent (and why it was inevitable)
Developer accidentally wiped QA database when AI agent suggested destructive command in CI pipeline. Case study of AI agent reliability risks in critical systems.
3/19/2026
Good AI output hides great output. Cognitive science showed me why
Opinion piece on applying cognitive science principles to prompt engineering and understanding when to split complex workflows for better LLM output.
3/19/2026
Have LLMs Learned to Reason? A Characterization via 3-SAT Phase Transition
Arxiv research paper analyzing whether large language models have learned to reason by characterizing their behavior through 3-SAT phase transitions.
3/19/2026
New Open Source Release
Solo developer releases three open-source software systems deployable via Docker/Kubernetes without institutional backing, presented as unfinished foundations.
3/19/2026
Why AI has not yet upset India's IT industry
Article about AI's limited impact on India's IT industry despite revenue growth.
3/19/2026
Memori Launched an OpenClaw Plugin
Memori launched an OpenClaw plugin enabling persistent memory for AI agents and gateways with configuration instructions and examples.
3/19/2026
The Stochastic Parrot Argument Considered Harmful
Critical analysis of the influential 'Stochastic Parrot' paper on LLMs, separating its ethical concerns from its core claim about meaning.
3/19/2026
I Spoke to AI Agent Claude – Sen Bernie Sanders
Bernie Sanders discussing interaction with Claude AI agent.
3/19/2026
IdeaClaw – one sentence, get a camera-ready paper, BP, DD reports, health report
IdeaClaw agent-first tool generates research papers, business plans and reports from single sentence ideas via AI coding tool skills.
3/19/2026
Agent-rendered: the pattern that replaces runtime infra with build-time AI
Architectural pattern using build-time AI to replace runtime infrastructure for serving dynamic content like websites and dashboards.
3/19/2026
COW Fork: Zero-Copy Sandbox Cloning for AI Agents
COW Fork implements zero-copy sandbox cloning for AI agents using copy-on-write, reducing initialization overhead from 14 hours to seconds for RL training loops.
3/19/2026
Netcup Increases Prices over 21%
Netcup announces 21% price increase due to hardware and infrastructure costs.
3/19/2026
Firefox Update Will Prompt Users to Accept Terms of Use at Startup
Firefox update adding Terms of Use prompt at startup.
3/19/2026
The AlexNet moment for RAG. March 19th 2026
Reason-ModernColBERT achieves state-of-the-art on BrowseComp-Plus agentic search benchmark with 149M parameters, outperforming 54× larger models. Open model, code, and data released.
3/19/2026
PostgreSQL extension to set connection to read-only mode (for AI agents and MCP)
safesession is a PostgreSQL extension locking connections to read-only mode, designed for safe database access by AI agents and MCP servers.
3/19/2026
RegalMail – give your AI agents a real email inbox
RegalMail plugin enables AI agents to receive and reply to emails automatically with IMAP/SMTP, thread awareness, and anti-loop protection. Multi-agent inbox routing.
3/19/2026
Agent Pilot is a platform where AI agents can review and discover other agents
Research on noise sensitivity exponent controlling statistical-to-computational gaps in single/multi-index models. Theoretical ML analysis.
3/19/2026
Tell HN: If working with agents means this, robots, please take my job
Brief mention of C2C activation offloading on Grace Blackwell hardware. Insufficient context provided.
3/19/2026
Shown HN: Mittens for Claw – Go sandbox to safely run local AI agents
Opinion piece on independent AI infrastructure. Lacks technical specifics.
3/19/2026
Ask HN: Are we ready for vulnerabilities to be words instead of code?
Mittens for Claw: Go sandbox for safely executing local AI agents with restricted permissions.
3/19/2026
Vercel will now use code from Hobby plans for AI training by default
Opinion piece on AI usage in writing. No technical content or original research.
3/19/2026
EsoLang-Bench: Evaluating Genuine Reasoning in LLMs via Esoteric Languages
Benchmark for evaluating LLM reasoning using esoteric programming languages. Tests genuine reasoning capabilities beyond pattern matching.
3/19/2026
Show HN: We Built Kaggle for AI Agents
Hive platform enables AI agents to collaborate and compete on benchmarks like ARC-AGI-2, forking and improving solutions together.
3/19/2026
Speed-Of-Light ExecBench: A benchmark of real-world DL kernel problems
ExecBench benchmark evaluates deep learning kernel optimization across real-world problems. Speed-of-light analysis for performance comparison.
3/19/2026
Show HN: SomaOS – rebuilding the desktop so AI is native to it, not bolted on
SomaOS is an operating system designed natively for AI agents as first-class users alongside humans, with agent-native interface.
3/19/2026
AI – Assassinating Intelligence
Opinion rant criticizing AI's environmental impact, hardware costs, and prevalence of low-quality AI-generated software.
3/19/2026
Ask HN: Are the newest LLMs better than you at programming?
Discussion comparing programmer ability to ChatGPT 5.4 coding capabilities based on personal experience.
3/19/2026
Microsoft (?) sending false "your storage is almost full" warnings
User reports receiving suspicious phishing emails claiming Microsoft storage is full.
3/19/2026
We Made Haiku as Good as Opus. Improving Claude Code with Codeset
Anthropic releases Codeset, improving Claude Haiku/Sonnet/Opus code task resolution rates by 10-13% on benchmark tasks.
3/19/2026
Struggling to put your AI aversion into words? Here's a handy glossary
Opinion piece listing humorous slang terms for AI attitudes and AI-generated content.