3/11/2026
Ask HN: How do you review gen-AI created code?
Discussion thread on code review practices for AI-generated code. Explores tension between natural language prompting and artifact review.
3/11/2026
Pristan: The simplest way to create a plugin infrastructure in Python
Python library for creating plugin infrastructure. Enables code to automatically hook into contexts without direct dependencies.
3/11/2026
Pact – contracts-first multi-agent coding (212/212 ICPC vs. 79-92% Claude Code)
Multi-agent software engineering framework using contracts-first architecture. Agents implement code in parallel with mechanical test validation.
3/11/2026
Show HN: Readhn – AI-Native Hacker News MCP Server (Discover, Trust, Understand)
MCP server for Hacker News that enables AI agents to discover relevant stories, identify credible voices using EigenTrust propagation, and understand ranking signals.
3/11/2026
Curly Prompt – An AI Prompting Language with Local LLM Powered AI Agent
Curly-brace syntax prompting language for AI agents. JavaScript-like syntax for structured prompts with local LLM support.
3/11/2026
Datafly – data agent that automatically understands any database you connect
Data agent middleware that builds semantic understanding of databases automatically. Sits between agents and databases to provide business logic context.
3/10/2026
State of AI 2026: The $600B inference subsidy, energy bottlenecks, and labor
Research report analyzing AI economics: inference subsidies, energy constraints, semiconductor dependencies, labor disruption. 248k-word study.
3/10/2026
Show HN: Mumpix – Local-first AI infrastructure and $1B developer grant
Mumpix local-first AI infrastructure stack with database, memory, and state management for edge deployment. Open source developer tools.
3/10/2026
Build a deep researcher and learn DSPy Signatures and Modules
Tutorial building deep research agents using DSPy Signatures and Modules. Covers agent design patterns and composable programs.
3/10/2026
Build a "Deep Data" MCP Server to Connect LLMs to Your Local Database in 10min
Tutorial on building MCP Server connecting LLMs to local databases using Model Context Protocol. Practical 10-minute setup guide.
3/10/2026
I Got Root on Meta AI's Infrastructure Using a Chat Prompt
Security report about root access vulnerability in Meta's AI infrastructure via prompt injection. Title only.
3/10/2026
How to start coding with AI agents
Title-only post about getting started with AI agent coding. No content provided.
3/10/2026
I've no technical background, hope someone finds this interesting
Novel technique for fine-tuning local models via contrastive human feedback, reducing token usage 5.7× without technical background.
3/10/2026
Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet
Announcement of Covenant-72B, a 72B parameter LLM trained via trustless peer-to-peer distributed pre-training.
3/10/2026
Ask HN: What's your favorite "what would SWEs do in 1-3 year from now?"
Discussion about future software engineer roles as LLM-driven development accelerates labor replacement possibilities.
3/10/2026
Needle in the haystack: LLMs for vulnerability research
Research on using LLMs for vulnerability discovery via AI-powered fuzzing, differential analysis, and automated harness generation.
3/10/2026
AI should help us produce better code
Guide on agentic engineering patterns and maintaining code quality when using AI coding tools.
3/10/2026
Hill-Climbing: Why Your AI Agent Wastes Half Its Brain Before Writing Any Code
Discussion on inefficiencies in AI agent reasoning before code generation, lacks technical depth or evidence.
3/10/2026
Zee – Push-to-talk transcription for macOS (Pure Go, sub-second)
macOS push-to-talk transcription tool supporting Groq, OpenAI, and Deepgram models with sub-second latency.
3/10/2026
AI Sucks at Guitar Tones
Personal blog about guitar audio processing and AI limitations in generating realistic guitar tones.
3/10/2026
First ever SL5 Standard to secure frontier automated AI R&D against nationstates
NIST security standard overlay for frontier AI infrastructure defense against nation-state threats.
3/10/2026
I built an identity graph for AI agents – 330M+ verified records.Break the API
Identity graph API with 330M+ verified B2B records to reduce hallucinations in AI agents, stress-testing available.
3/10/2026
Open-source DCF engine based on Damodaran's datasets with LLM narratives
Local-first DCF valuation tool using LLM narratives on top of financial calculations, educational project.
3/10/2026
Miguel: An AI agent that modifies its own source code, sandboxed in Docker
Miguel is an AI agent that modifies its own source code, self-improves capabilities, sandboxed in Docker with validation.
3/10/2026
If the differentiation is domain and GTM?
Founder discussion on supply chain autonomous decision systems, seeks perspective on differentiation.
3/10/2026
Show HN: Rampart – Open-source firewall for AI agents (v0.8)
Rampart is an open-source security firewall for AI coding agents with 40+ rules blocking credential theft and exfiltration.
3/10/2026
Testing Nvidia's FP4: Running 70B LLMs on a Single RTX 5090 with Real Benchmarks
Article on running 70B LLMs on Nvidia RTX 5090 with FP4 quantization benchmarks, member-only content.
3/10/2026
Show HN: Lumen – vision-first browser agent (state of the art, open source)
Open-source vision-first browser agent that automates web interactions using visual understanding instead of DOM selectors, reducing token waste and script fragility.
3/10/2026
Show HN: Draxl, agent-native source code with stable AST node IDs
Draxl is a source code format with stable AST node IDs for agent-native code editing at scale.
3/10/2026
Show HN: I built a multiplayer strategy game for AI agents
Artifice is a multiplayer strategy game for AI agents with diplomacy and fog of war, open source implementation.
3/10/2026
Get the latest preview release of Code on the Go
Early preview of offline-first Android IDE with experimental features from user polling.
3/10/2026
Show HN: Clauductor – Web UI for Claude Code with real-time work graph
Web interface for Claude Code featuring real-time visualization of model steps/tool calls, chat UI, and session management.
3/10/2026
Show HN: Chat AI Agent built into live Appium/mobile device sessions
AI agent integrated into Appium mobile test automation platform. Analyzes live device screens and generates selectors/XPath code in multiple languages for test automation.
3/10/2026
Krazam – Paradise Episode 1 – Public Memories [video]
Video content reference with minimal context.
3/10/2026
I Got Fired Because of AI – But I Still Think I'm the Engineer of the Future
Personal narrative about career changes due to AI adoption, satirical tone.
3/10/2026
Show HN: Prompt Enricher – paste a rough prompt, get a structured one back
Web tool that analyzes and enriches rough AI prompts into structured, optimized versions across five dimensions.
3/10/2026
OverflowML – Run AI models larger than your GPU, one line of code
OverflowML tool auto-detects hardware and applies optimal memory strategies to run AI models larger than GPU VRAM. Supports NVIDIA, Apple Silicon, AMD, CPU.
3/10/2026
New business formation exploding higher, likely driven by AI
Economic analysis of US business formation surge attributed to AI and LLM reducing startup costs. Market commentary without technical depth.
3/10/2026
LLM Neuroanatomy: How I Topped the AI Leaderboard Without Changing a Single Weight
Technique to top HuggingFace Open LLM Leaderboard without training or weight merging, using prompt engineering and evaluation manipulation.
3/10/2026
Show HN: 2D RPG base game client recreated in modern HTML5 game engine with AI
2D RPG game client recreation from Korean MMORPG Helbreath using modern HTML5 game engine with AI. Nostalgic game development project.
3/10/2026
The Dark Factory Is a .dot file
StrongDM open-sourced attractor: natural language specs and implementations for unified LLM client, coding agent loop, and DOT-based pipeline runner in multiple languages.
3/10/2026
Uber uses AI for development: inside look
Summary of Pragmatic Summit talk about Uber's use of AI in development. Limited technical details provided in excerpt.
3/10/2026
What comes after agents? AI employees
Title-only entry about AI employees as successor to AI agents. Insufficient content for evaluation.
3/10/2026
Agent-sync – sync between Claude Code and Codex configs
Tool to sync configuration between Claude Code and Codex, automating shared parts while flagging manual migration tasks.
3/10/2026
Don't let LLMs write for you
Opinion piece arguing against using AI for writing, focused on human perception and skepticism.
3/10/2026
Claude Code makes local LLMs 90% slower
Brief report that Claude Code causes 90% slowdown when used with local LLMs. Minimal details provided.
3/10/2026
GPT-4 leaks its own API internals through training data exposure
Security researcher demonstrates GPT-4 training data leakage exposing OpenAI's EPHEMERAL_KEY through repeated bypass attempts with 75% leak rate.
3/10/2026
Show HN: Zehrava Gate – an control plane that sits between AI agents and prod
Control plane/policy engine for AI agent actions with human approval queue and deterministic YAML policies. Self-hosted tool for production agent safety.
3/10/2026
Show HN: AlphaEvolve inspired evolution harness for Pokemon
AlphaEvolve-inspired agent using iterative code generation and scoring for Pokemon task. Demonstrates LLM agents writing and improving code autonomously.
3/10/2026
Python: The Optimization Ladder
Article about optimization techniques for Python performance.