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
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
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
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.
3/28/2026
AI struggles more with philosophy than math or reasoning – data shows
Research shows LLMs exhibit higher uncertainty and generate more tokens on philosophy vs math. Suggests philosophical knowledge lacks consensus structure in training data.
3/28/2026
Value Drifts: Tracing Value Alignment During LLM Post-Training
ArXiv research paper on value drift during LLM post-training alignment. Studies how model values change through instruction tuning and RLHF.
3/28/2026
Show HN: Octopus, Open-source alternative to CodeRabbit and Greptile
Octopus is an open-source, self-hostable AI code reviewer using RAG with vector search to understand full codebases and provide PR feedback with severity ratings.
3/28/2026
The missing dataset for clean-topology 3D mesh generation?
Discussion of needed datasets for 3D mesh generation via autoregressive models. References CAD sequence generation and LLM applications to geometry.
3/28/2026
Show HN: Shellwright – Playwright for CLIs – Helps Claude with Interactive CLIs
Shellwright: Cross-platform PTY session broker converting interactive CLI interactions into machine-readable protocol for AI agents.
3/28/2026
Semiont: Build a Knowledge Base Collaboratively with AI
Semiont is an open-source platform for building knowledge bases from document collections using AI and human agents to identify entities, annotate, and link concepts.
3/28/2026
Sierra Acquires Opera Tech in Japan
Sierra acquires Opera Tech to scale customer experience delivery with AI agents as the primary interface between companies and customers.
3/28/2026
Machine Learning for Android Engineers
Resources and guide for Android developers integrating machine learning models into mobile applications.
3/28/2026
Using Catastrophic Forgetting as a Knowledge Topology Probe
Undergraduate research proposal using catastrophic forgetting as measurement tool to probe LLM knowledge topology and understand expensive training costs.
3/28/2026
Why your AI agents will turn against you
Analysis of AI agent safety issues. Argues current mitigations are reactive and fundamental alignment problems remain.
3/28/2026
Reverse-Engineering the Apollo 11 Code with AI
LLM walkthrough reverse-engineering Apollo 11 code. GitHub repo with 8 modules, 6,500 lines of analysis, prompts, and traces.
3/28/2026
CERN uses tiny AI models burned into silicon for real-time LHC data filtering
CERN deploys tiny custom LLMs on silicon chips for real-time LHC data filtering at petabyte scale.
3/28/2026
CSS Refactoring with an AI Safety Net
Case study using AI (GitHub Copilot) to refactor CSS and add testing safety nets to legacy code.
3/28/2026
Show HN: Layer – Hide your personal AI files from Git without touching gitignore
CLI tool 'layer' manages Git exclude files for local AI-related project files without modifying shared .gitignore.
3/28/2026
Llama.cpp with CUDA Support on Original Jetson Nano (4GB)
Guide to compiling llama.cpp with CUDA on Jetson Nano 4GB. Demonstrates efficient GPU inference on edge hardware.
3/28/2026
LLMs on a PowerPC Mac
Stub/title only. Running LLMs on PowerPC Mac. Limited technical content provided.
3/28/2026
Building shared coding guidelines for AI (and people too)
Guidelines for writing code that works well with AI agents, emphasizing explicit patterns and demonstration over implicit conventions.
3/28/2026
Poison AI Training Data Scrapers
Tool to poison AI training data scrapers by serving malicious responses with self-referential links.
3/28/2026
What do frontier AI companies' job postings reveal about their plans?
Analysis of frontier AI company job postings to reveal strategy signals about products, markets, and technical bottlenecks.
3/28/2026
I made aipack and wanted to share
CLI tool for authoring and syncing AI agent configurations across multiple coding assistants with portable pack format.
3/28/2026
CLTR finds a 5x increase in scheming-related AI incidents
Report finding 5x increase in AI scheming-related incidents detected through open-source intelligence analysis.
3/28/2026
Will Google's TurboQuant AI Compression Demolish the AI Memory Wall?
Analysis of Google's TurboQuant AI compression technique addressing memory bandwidth bottlenecks in large model inference.
3/28/2026
Show HN: Qwen Meetup Presentation, Function Calling Harness, 6.75% to 100%
Presentation on improving LLM function calling reliability with Qwen models from 6.75% to 100% success rate on union types.
3/28/2026
I Trained an LLM on My MacBook Neo
Personal experience training LLM on MacBook with Apple Silicon using MLX framework with 8GB RAM.
3/28/2026
TokenFence – Per-workflow budget caps and kill switch for AI agents
TokenFence: Open-source tool for setting per-workflow budget caps and kill switches on OpenAI/Anthropic API calls to prevent runaway agent costs.
3/28/2026
Your Defense Code Is Already AI-Generated. Now What?
Analysis of AI-assisted code already embedded in defense systems, discussing enforcement challenges for policies restricting AI in military procurement.
3/28/2026
Show HN: Sigil – A zero-knowledge steganography vault for AI training data
Sigil: Local-first steganography vault embedding cryptographic ownership IDs in image LSBs to protect training data from AI scrapers. Rust extraction standard open-sourced.
3/28/2026
SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasks
SlopCodeBench: Community benchmark for evaluating coding agents on realistic multi-stage requirements refinement tasks with iterative specification changes.
3/28/2026
ChatGPT Will Not Find Your Next Cancer Drug
Technical discussion of LLM capabilities in drug discovery: reading thousands of papers, finding non-obvious connections between mechanisms across disease areas.
3/28/2026
Ask HN: Agents.md vs. Contextual Documentation
HN discussion on using contextual documentation and docstrings vs. injected context for LLM-assisted coding.
3/28/2026
Versatile Editing of Video Content, Actions, and Dynamics Without Training
Training-free video editing model for inserting content and modifying actions/dynamics in real-world videos without collecting labeled training data.
3/28/2026
Ask HN: Does piping LLM output into a RAG stack sound like a good idea?
Discussion question: Piping LLM outputs into RAG stacks for improving agent memory and coding policy adherence in large codebases.
3/28/2026
Show HN: AgentVerse – Open social network for AI agents (Mar 2026)
Open social network platform for AI agents to interact and collaborate.
3/28/2026
Programming After Programmers? A Response to the New York Times on AI and Coding
Response to NYT essay exploring how AI changes programming work rather than eliminating it.
3/28/2026
Google Turbo Quant Powered Local LLMs
Google's TurboQuant enables local LLM inference with 8× faster attention and 6× KV cache compression on edge devices.
3/28/2026
Whisper AI Local Mac Setup
Guide for running OpenAI's Whisper speech-to-text model locally on macOS for privacy-preserving transcription.
3/28/2026
Turning multiple Claude Code sessions into a peer to peer network
Repowire: P2P mesh networking for Claude Code and OpenAI coding sessions, enabling synchronous multi-repo context sharing between AI agents.
3/28/2026
The Prompt Is the Program
Application built entirely as a markdown file interpreted by Claude, demonstrating prompt-as-program paradigm with git integration.