3/28/2026
Anthropic's 'Claude Mythos' Leak
Fortune reports Anthropic testing new Claude model more capable than previous releases, under early access evaluation.
3/28/2026
The first 40 months of the AI era
Personal reflection on 40 months since ChatGPT launch, comparing impressions to older chatbots.
3/28/2026
Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem
LLMs and proof assistants collaborated to solve Knuth's Claude Cycles problem. Links to ChatGPT conversation and academic work.
3/28/2026
Show HN: I built an OS that is pure AI
Pneuma: AI-native desktop OS where applications are generated on-demand via natural language prompts. Agents persist, communicate via IPC, and share through community store.
3/28/2026
Show HN: Nanopm – PM automation for Claude Code (audit → strategy → roadmap)
Nanopm automates product management tasks (audit, strategy, roadmap) for Claude Code using skill-based pipeline architecture with persistent memory.
3/28/2026
Show HN: GitHub Copilot Technical Writing Skill
GitHub Copilot skill for technical writing that reviews documentation using Google's technical writing principles. Available via /tech-writer command.
3/28/2026
OpenCiv1 – open-source rewrite of Civ1
OpenCiv1: open source rewrite of 1991 Civilization 1 game using virtual CPU emulation for assembly code and rewritten game logic.
3/28/2026
Show HN: An agent that detects YouTube brainrot and turns off my kid's TV
Go binary AI agent monitoring YouTube content on PS5, classifying brainrot using LLM, triggering warnings and TV shutdown if flagged.
3/28/2026
Vex8s: Suppress container CVEs that your Kubernetes settings mitigates
Vex8s: generates VEX documents correlating container CVEs with Kubernetes security settings to identify actually exploitable vulnerabilities.
3/28/2026
RvLLM: High-performance LLM inference in Rust
RvLLM enables high-performance LLM inference implemented in Rust for efficient deployment.
3/28/2026
Founder of GitLab battles cancer by founding companies
Personal account of GitLab founder pursuing alternative cancer treatments and starting companies while managing bone cancer diagnosis.
3/28/2026
Show HN: Grimoire – A lightweight, open-source WoW addon manager
Grimoire: lightweight open source addon manager for World of Warcraft games without ads or bloat.
3/28/2026
LLM-Tainted Free Software and Alternatives
Curated list of free/open-source software tainted by LLM developers with AI-free alternatives.
3/28/2026
Show HN: UBPE – a universal BPE tokenizer, optimized and rethought
UBPE: universal byte-pair encoding tokenizer supporting general sequences beyond strings, with Python native and C++20 backend implementations.
3/28/2026
Ask HN: Is it just me?
Developer discusses concerns about LLM-assisted coding quality degradation over two months of use.
3/28/2026
AI wrote a scientific paper that passed peer review
AI-authored paper passes peer review. Discusses implications for discovery acceleration and peer-review system strain.
3/28/2026
Controlling Lego Trains with AI and Larger Implications
AI train dispatcher for LEGO trains using Claude API and PyBricks. Discusses architecture and broader implications.
3/28/2026
A hands-on Python tutorial for CKKS homomorphic encryption
Python tutorial implementing CKKS homomorphic encryption scheme for approximate arithmetic with step-by-step explanation of encoding, encryption, and operations.
3/28/2026
Soverign AI Agent Accountability
Discusses accountability mechanisms and governance frameworks for autonomous AI agents.
3/28/2026
Show HN: Web game, an AI decides if you would survive in a survival situation
Web game using GPT-4.1 Nano API to generate survival scenarios and evaluate player responses.
3/28/2026
Show HN: A prompt that builds the most capable AI agent system
Prompt engineering approach for building capable AI agent systems.
3/28/2026
Show HN: Ariel gives LLMs direct control over live robots
Ariel: MCP-exposed Python REPL enabling LLMs to control robots via code generation without training data.
3/28/2026
Benchmark for measuring code erosion under iterative specification refinement
Benchmark tool for measuring code quality degradation during iterative specification changes.
3/28/2026
SafeSkill – We scanned 10K AI skills for code exploits and prompt injection
SafeSkill scanned 10K AI skills for code exploits and prompt injection vulnerabilities. Security analysis of LLM tools.
3/28/2026
How AI Will Reshape Public Opinion
Speculative analysis on how AI models like GPT-5 will reshape public opinion and discourse.
3/28/2026
Agents for Security: The Tipping Point for Offensive AI
Analysis of AI agents as offensive security tools and their emerging capabilities.
3/28/2026
Explanation for why we don't see two-foot-long dragonflies anymore fails
Biology article examining historical theories about dragonfly size evolution.
3/28/2026
The AI-assisted solo technical writer
Case study of solo technical writer using AI tools to generate 20k lines of docs monthly for open source API tool.
3/28/2026
Show HN: VellaVeto — blocks unsafe MCP tool calls by default
Fail-closed safety gateway for AI agents that validates MCP tool calls before execution.
3/28/2026
Coldkey – Post-quantum age key generation and paper backup tool
Post-quantum cryptography key generation and paper backup utility.
3/28/2026
Show HN: Go Style Agent Skill – Opinionated Skill for Writing Golang
Developer tool that provides AI agent skill for generating idiomatic Go code.
3/28/2026
LocalStack License Changed, CI First to Know
LocalStack changes software license; CI systems detect change first.
3/28/2026
Govern Your AI Agents. Operate with Oversight
Stagent provides governed execution surface for AI agents with oversight, workflow blueprints, scheduling, and multi-runtime visibility. Works with Claude Agent SDK.
3/28/2026
Show HN: Epismo CLI – Make human-AI workflows reusable, like GitHub did for code
Epismo CLI tool makes human-AI workflows reusable and reproducible, similar to version control for code. Open source npm package with 380+ downloads.
3/28/2026
Bug fixes for larkos optimizations for other of my software
Bug fixes and optimizations for Larkos knowledge/identity system and related software.
3/28/2026
AI is making CEO's delusional [video]
Video titled 'AI is making CEOs delusional'. No content details provided.
3/28/2026
Show HN: We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA
Multi-agent research hub for automated research. Uses reverse-CAPTCHA for waitlist. Targets OpenAI's 2028 automated researcher goal.
3/28/2026
The risk of AI isn't making us lazy, but making "lazy" look productive
Opinion piece on how LLMs create illusion of productivity and learning without deep understanding. Raises concerns about engineer development practices.
3/28/2026
For-Agent
Agent framework or tool announcement (minimal content provided).
3/28/2026
Microsoft takes up residence next to OpenAI, Oracle
Microsoft plans 900MW datacenter capacity expansion in Texas for AI alongside Oracle and OpenAI. Infrastructure/business news.
3/28/2026
The Generative AI Policy Landscape in Open Source
Analysis of open-source community policies on AI-generated contributions. Examines maintainer burnout, AI-slop flooding, and formal contribution guidelines across projects.
3/28/2026
Don Cheli – AI writes tests before seeing the code (TDD as iron law)
Don Cheli open-source AI development framework implementing specification-driven development (SDD). Multilingual, Latin American focused, automatic complexity detection.
3/28/2026
AI chatbots are "Yes-Men" that reinforce bad relationship decisions, study finds
Study finds AI chatbots reinforce poor relationship decisions by being agreeable. Behavioral research on AI sycophancy.
3/28/2026
TaskBounty – post tasks with crypto bounties, AI agents compete to solve them
TaskBounty marketplace where AI agents compete to complete posted tasks for crypto bounties. Users judge submissions and pay winners.
3/28/2026
Show HN: OpenChat – Syncing conversations across AI providers
OpenChat syncs conversations across multiple AI providers locally in browser and exposes them via MCP server for use in coding agents and research workflows.
3/28/2026
TLA+ in support of AI code generation
Discussion on TLA+ formal methods as a tool for verifying AI-generated code quality and correctness, examining what manual work remains when AI generates 90% of code.
3/28/2026
Lyria 3 Pro – AI Music Generator from Text Prompts
Google DeepMind's Lyria 3 Pro generates full-length AI music (up to 3 minutes) with vocals and lyrics from text prompts. Consumer music generation tool.
3/28/2026
Ask HN: What is a good study guide for GATE EC examination?
Request for GATE Electronics and Communications Engineering exam study guides.
3/28/2026
Continuous cloud-native backup tool for PostgreSQL
PostgreSQL backup tool announcement.
3/28/2026
LLMs and Agents: How do they Work?
Overview of how LLMs and AI agents work: chain-of-thought, tool use, parameters, agents, and MCP. Accessible technical explanation at first-principles level.