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
RvLLM: High-performance LLM inference in Rust
RvLLM enables high-performance LLM inference implemented in Rust for efficient deployment.
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: 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
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
Agents for Security: The Tipping Point for Offensive AI
Analysis of AI agents as offensive security tools and their emerging capabilities.
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
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
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.