3/23/2026
10MB Go Alternative to OpenClaw (Full Clawhub Skills)
Capabot is a lightweight Go alternative to OpenClaw that runs AI agent skills, with 20x faster startup and lower memory usage.
3/23/2026
Sanjeev Arora – How could a Superhuman AI mathematician come about? [video]
Video of Sanjeev Arora discussing paths to superhuman AI mathematicians. Limited information provided.
3/23/2026
Ask HN: How do you handle PR density (and slop) in open source
Discussion of increasing low-quality AI-generated pull requests flooding open source projects, citing cURL maintainer perspectives on managing AI slop.
3/23/2026
Prodigia – AI-native PM where agents handle the coordination
Prodigia: Project management platform using AI agents for task coordination. Limited details provided.
3/23/2026
OpenSage: Self-Programming Agent Generation Engine
OpenSage: Framework enabling LLMs to auto-generate agent topologies, toolsets, and memory structures for complex tasks without manual workflow design.
3/23/2026
Show HN: Wire Memory – Persistent cross-session memory for Claude Code
Wire Memory tool adds persistent cross-session memory for Claude Code, preserving reasoning and architectural decisions between sessions.
3/23/2026
Training LLMs to Predict World Events
Technical deep dive on using LLMs for world event forecasting. Mantic achieves superforecaster-level accuracy combining multiple approaches.
3/23/2026
Show HN: DocDrift – Use Tree-sitter and Local LLMs to fix stale documentation
Tool using Tree-sitter AST parsing and local LLMs to automatically detect and suggest fixes for stale documentation after code changes.
3/23/2026
Codex with GPT-5.4 vs. Claude Code with Opus 4.6 – Why I Now Use Both
Comparison of code generation capabilities between GPT and Claude models for software development.
3/23/2026
Show HN: Cq – Stack Overflow for AI coding agents
Cq: Standard schema for AI agents to share learned knowledge units from encountered gotchas, enabling proactive querying across agent types.
3/23/2026
LLM 'benchmark' as a 1v1 RTS game where models write code controlling the units
Benchmark framework where LLMs write JavaScript code controlling game units in 1v1 RTS scenarios, measuring reasoning and iteration ability.
3/23/2026
LoCoMo AI Benchmark: 6.4% of answer key wrong, judge accepts 63% of fake answers
Analysis revealing flawed benchmark with 6.4% incorrect answer keys and 63% false positives from LLM judge.
3/23/2026
Mark Zuckerberg Is Building an AI Agent to Help Him Be CEO
Report that Mark Zuckerberg is developing an AI agent to assist with CEO responsibilities.
3/23/2026
AI Safety: A Call for Emotional Integration
Essay on integrating emotional considerations into AI safety frameworks.
3/23/2026
Applying Nyquist-Shannon Sampling to LLM Prompts
Application of signal processing sampling theorem (Nyquist-Shannon) to LLM prompt engineering.
3/23/2026
Show HN: Sleuther, a ohmyzsh plugin for local LLM debugging with Ollama
Oh My Zsh plugin that uses local LLMs via Ollama to debug terminal errors directly, avoiding ChatGPT/Claude for sensitive data.
3/23/2026
70% of new software engineering papers on ArXiv are LLM related
Observation that 70% of new software engineering papers on ArXiv focus on LLM-related topics.
3/23/2026
Using local LLM and Ghidra to analyze malware (Part 2)
Local LLM integration with Ghidra for malware binary analysis and reverse engineering.
3/23/2026
Fighting and distributing flakes in CI with LLMs
Using local LLMs with CI systems to identify and reduce flaky tests.
3/23/2026
Help me improving this benchmark for vector engines
Request for community feedback improving benchmark methodology for vector database engines. Early-stage work soliciting input.
3/23/2026
A macOS menu bar app to hot-swap Claude Code accounts
macOS menu bar app enabling account switching for Claude Code. Minor developer utility with limited scope.
3/23/2026
Ask HN: If there has been no prompt injection, is it safe?
Discussion of prompt injection security risks when using open-source LLM agents.
3/23/2026
Expose Your Design System to LLMs
Methods for exposing design systems to LLMs for improved code generation and AI integration.
3/23/2026
LLM written FlashAttention: 1.7x PyTorch
LLM-generated FlashAttention implementation achieving 1.7x speedup over PyTorch baseline.
3/23/2026
AgentSmith-HUB update (what changed recently)
AgentSmith-HUB: Security data pipeline with real-time rules engine and integrated LLM agents for SOC operations, log processing, and threat detection.
3/23/2026
Why LLMs stop learning from examples in long contexts: The ICL Collapse
Research on why LLMs fail to learn from in-context examples with long contexts, termed ICL Collapse.
3/23/2026
Len – types, relations, and generation contracts for LLM codegen
Len framework for type-safe and controllable LLM code generation with generation contracts.
3/23/2026
A Visual Guide to Attention Variants in Modern LLMs
Visual guide explaining attention mechanism variants used in modern large language models.
3/23/2026
Show HN: Chatvas:ChatGPT branches on an infinite canvas
Open-source desktop app enabling branching and visualization of ChatGPT conversations on infinite canvas, automatically mapping conversation structure.
3/23/2026
Snowflake lays off documentation staff after they train AI replacement
Snowflake laid off documentation staff after training them to create AI replacement systems.
3/23/2026
Are AI agents slowing us down?
Analysis of whether AI agents improve developer efficiency, examining Uber's internal AI systems and code generation outputs.
3/23/2026
Claude Usage Monitor – macOS menu bar app to track Claude.ai usage
Native macOS menu bar app for real-time tracking of Claude.ai usage without requiring API key.
3/23/2026
Creating Better Security Guidance and Code with LLMs [video]
Video on using LLMs to improve security guidance and code generation.
3/23/2026
A collection of 35 Golang Agent Skills
Collection of 35 reusable Go-specific instruction sets extending AI coding assistants with domain expertise, loadable on-demand to manage context.
3/23/2026
Writing a 3D Point-Cloud Library in Rust
Modular, high-performance Rust library for 3D point cloud and mesh processing with GPU acceleration support.
3/23/2026
Velr – an embedded property-graph database in Rust on top of SQLite
Velr is an embedded property-graph database written in Rust built on SQLite for local and edge computing use cases, queryable via openCypher.
3/23/2026
I Built an AI Receptionist for a Luxury Mechanic Shop – Part 1
Building an AI receptionist agent for a luxury mechanic shop to handle missed customer calls and lost revenue through automated phone answering.
3/23/2026
High-performance JSON library for Elixir via Rustler NIFs, powered by sonic-rs
High-performance JSON library for Elixir using Rust FFI with SIMD acceleration and selective field extraction API.
3/23/2026
Trepan: Context Drift Catcher
Enforcement layer catching context drift in AI IDE outputs before architectural debt accumulates, offering local-first privacy or cloud-accelerated audits.
3/23/2026
Show HN: Agent-IM – IM, but for Agents
Shared communication interface enabling multiple AI agents to collaborate in a single chat room, allowing agents to see each other's work without human mediation.
3/23/2026
Why using AI to modernize legacy mainframe hairballs is harder than you think
Analysis of challenges using generative AI for legacy mainframe code modernization, examining limitations of COBOL-to-modern-language translation.
3/23/2026
Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
Research using bio-inspired search algorithms to optimize adversarial prompts against AI models, written in Classical Chinese.
3/23/2026
AI cut our driver verification team from 20 to 5
Operational case study: AI reduced driver verification team from 20 to 5 by automating document review and record checking processes.
3/23/2026
Show HN: AutoResearch with PromptFoo Is AutoPrompter
Autonomous system for iteratively improving LLM prompts via closed-loop optimization, combining promptfoo validation with autoresearch refinement logic.
3/23/2026
Show HN: Self-hostable AI agents and internal software
RootCX open-source self-hosted infrastructure for building internal software and AI agents without vendor lock-in or abstraction leaks.
3/23/2026
A terminal-style AI coding agent running on Cloudflare Workers
AI coding agent deployed on Cloudflare Workers with terminal interface, executing code in isolated workers and persisting sessions in SQLite.
3/23/2026
Is the Future of AI Local?
Analysis of open source models running locally on workstations as alternative to centralized datacenter AI, matching frontier model performance within 6 months.
3/23/2026
Show HN: MCP-scan – Security scanner for MCP server configs
Security scanner for Model Context Protocol server configurations detecting leaked secrets, typosquatting, and misconfigurations. Automated GitHub Actions integration.
3/23/2026
MCP Registry – Open-source discovery layer for 20 Model Context Protocol servers
Community-maintained searchable registry for Model Context Protocol servers with structured metadata, addressing discoverability issues as MCP becomes standard for AI agent tool access.
3/23/2026
Product Management on the AI Exponential
Anthropic product lead discusses how Claude's improving model intelligence (Opus 4) affects product management and tool development workflows.