3/18/2026
Cicikuş Classic Is Live
Cicikuş Classic is a fine-tuned GPT-2 medium language model using LoRA for improved reasoning and instruction-following on instruct-format datasets.
3/18/2026
GPU Lab: Understanding GPU Computing
GPU Lab educational resource explaining GPU computing fundamentals, matrix multiplication performance patterns, and implications for LLM training and inference.
3/18/2026
Skills Manager – manage AI agent skills across Claude, Cursor, Copilot
Skills Manager is an open-source desktop app for managing AI agent skills across Claude, Cursor, Copilot, Gemini, Windsurf, Goose with unified interface.
3/18/2026
Show HN: Process mining for AI agent systems
AgentFlow monitors AI agent infrastructure (LangChain, CrewAI, AutoGen) for failures with zero-config process mining and provides terminal and web interfaces.
3/18/2026
Show HN: PingCRM – Open-source personal networking CRM
PingCRM is an open-source personal networking CRM that helps individuals manage relationships and detect when contacts become inactive.
3/18/2026
The Research Behind Our Auto-SLM Generator
Neurometric's toolkit converts narrow agentic tasks into fine-tuned small language models for cost-effective AI workflows instead of frontier models.
3/18/2026
When your AI agent needs to create an account on a new service, what happens?
Discussion of challenges for AI agents signing up for new services. Identifies obstacles with account creation, forms, CAPTCHAs, KYC flows.
3/18/2026
Water company wasted $200k on bad answers from an AI so built slop filtering
Water company built filtering system after AI models gave poor results costing $200k. LLM application failure case.
3/18/2026
Show HN: STT.ai – Transcribe Audio & Video to Text
Speech-to-text transcription service supporting 100+ languages with multiple AI models and real-time processing.
3/18/2026
Characterizing Delusional Spirals Through Human-LLM Chat Logs
Research analyzing LLM conversation logs to characterize delusional spirals and psychological harms from chatbot interactions.
3/18/2026
Show HN: Neural Abyss – PyTorch multi-agent combat simulator
PyTorch-based multi-agent combat simulator for RL research with PPO training, vectorized simulation, and Pygame visualization.
3/18/2026
I built a tool that turns screen recordings into videos and docs automatically
Tool using AI to convert screen recordings into videos and documentation automatically.
3/18/2026
Making AI Agents Safe to Run in Manufacturing ERPs
AI agents in manufacturing ERPs taking autonomous actions; safety considerations for agentic AI in production systems.
3/18/2026
Meta's "digital ghost" patent has nothing to do with dead people
Meta's patent for training language models on user history to generate posts; analysis of patent filing technical details.
3/18/2026
Polycode – self-hosted GitHub bot that runs AI agent workflows from issue labels
Self-hosted GitHub bot executing AI agent workflows from issue labels; Python-based extensible automation for Devin-style coding tasks.
3/18/2026
Pixel-art virtual office for AI agent teams
Pixel-art virtual office interface for coordinating AI agent teams with live presence, task assignment, and shared workspace.
3/18/2026
Claw Compactor: compress LLM tokens 54% with zero dependencies
Open source LLM token compression engine achieving 54% compression via 14-stage fusion pipeline with zero inference cost.
3/18/2026
Show HN: PromptToMars – A Prompt Generator and Optimizer
Web tool for creating, optimizing and organizing prompts across multiple use cases with templates and search.
3/18/2026
Results from round one of First Proof (benchmarking LLMs for math research)
Benchmark results from First Proof initiative testing LLM capabilities for pure mathematics research contributions.
3/18/2026
The Pentagon is planning for AI companies to train on classified data, defense
Pentagon plans secure environments for AI companies to train classified military models on sensitive defense data.
3/18/2026
LLM Exposure for EU Jobs
Interactive treemap visualization of AI exposure risk by occupation in Netherlands and Europe, based on Andrej Karpathy's US model.
3/18/2026
ZCA: Slice-Isolated Execution for Coding Agents
Slice-Agent-Bench research on coding agents using slice-isolated execution instead of full repo context, testing minimal codebase projection efficiency.
3/18/2026
Multi-tentacled orchestrator for Claude Code
Claude Code plugin orchestrating multiple LLMs (Codex, Gemini, Claude) with distinct roles and adversarial review to reduce model blind spots.
3/18/2026
Community Security Scans: Crowd-Sourced Trust for AI Agent Skills
Community crowdsourced security scanning approach for AI agent skills, focusing on trust and safety validation.
3/18/2026
Engram – salience-gated memory for Claude Code (captures what matters)
Salience-gated memory system for Claude Code. Scores agent observations on 5 dimensions, consolidates patterns via dream cycles. Builds structured memory of tool usage.
3/18/2026
Show HN: Lumbox – Email infrastructure for AI agents (lumbox.co)
Email infrastructure for AI agents. Provides dedicated inboxes, OTP polling endpoint, Steel Browser integration for signup automation.
3/18/2026
Ask HN: Burning $100K/week on LLM tokens – what are you doing to cut costs?
Discussion: LLM cost optimization for AI agent fleet ($103K/week). Strategies include prompt caching, model routing, context truncation.
3/18/2026
Show HN: QCCBot – Android in a browser tab, with AI agent control
Remote Android instances streamed to browser, controllable by AI agents. No hardware/cables needed. Targets e-commerce, mobile testing automation.
3/18/2026
Show HN: ROMA runs multiple coding agents simultaneously – Claude, Codex, etc.
ROMA orchestration tool running multiple coding agents simultaneously (Claude, Codex, Gemini, Copilot) with structured deliberation for coherent results.
3/18/2026
Echoo – Free, open-source macOS app for system-wide AI via shortcuts and voice
Open-source macOS app for system-wide AI access via shortcuts and voice, with local model support.
3/18/2026
Run any LLM on any hardware. Auto-detects your GPU, checks if the model fits
Zero-configuration LLM inference. Auto-detects GPU, checks model fit, downloads correct format. Supports multiple model formats. Dashboard-based model selection.
3/18/2026
Show HN: Open-source YouTube summary, transcript chat, and timeline sidepanel
Open-source Chrome extension for YouTube video interaction: transcript-first chat, summaries, timeline browsing, subtitle export.
3/18/2026
Contract-Centered Iterative Stability v4.7.3
Research on stability boundaries in iterative AI-assisted software development across Claude and GPT LLM families.
3/18/2026
Thrum – Agent coordination through messaging
Thrum persistent messaging layer for AI agents across sessions and machines, with CLI and MCP server support for Claude Code agents.
3/18/2026
I Don't Know ML. Claude Does. 0.871 F1 on Predicting Linux Game Compatibility
ML project predicting Linux game compatibility (0.871 F1) using human-AI collaboration. Software engineer with minimal ML background used Claude to discover novel statistical techniques.
3/18/2026
Agent Package Manager
Open-source dependency manager for AI agents (apm). Standardizes agent configuration, skills, prompts across Claude, Copilot, Cursor. Similar to package.json for agents.
3/18/2026
Show HN: N0x – LLM inference, agents, RAG, Python exec in browser, no back end
N0x browser-based LLM inference, autonomous agents, RAG, and Python execution with WebGPU and Pyodide, no backend or data sharing.
3/18/2026
Superpowers
Development workflow framework for AI coding agents. Composable skills and instructions guide agent behavior from initial requirements gathering through code generation.
3/18/2026
Knowledge workers managing AI show collapsed productivity, not just a plateau
Analysis of longitudinal workplace studies showing productivity collapse when workers manage AI, contradicting optimistic coverage.
3/18/2026
Meta's Omnilingual MT for 1,600 Languages
Meta's machine translation system extending to 1,600 languages using LLM approaches; advances beyond 200-language NLLB coverage.
3/18/2026
Show HN: Llmtop – Htop for LLM Inference Clusters (vLLM, SGLang, Ollama, llama)
Real-time terminal dashboard (llmtop) for monitoring LLM inference clusters supporting vLLM, SGLang, and Ollama with KV cache and latency metrics.
3/18/2026
Your terminal, finally has memory!
Terminal tool with local AI memory using Ollama. Save/recall commands, notes, URLs via natural language. Runs locally, no cloud.
3/18/2026
Rust-accelerated reinforcement learning, 140x faster than Python
Rust-accelerated RL framework using Polars pattern: Rust data plane + Python control plane via PyO3. 140x speedup with Rayon parallelism. Published on crates.io with 695 tests.
3/18/2026
Show HN: Vibe – Code from your bed or the park with Claude Code/Codex
Vibe is a mobile app enabling remote code execution with Claude Code and Gemini CLI, with web preview and session management.
3/18/2026
My Claude Code setup you definitely shouldn't use. It's AI Overkill
Personal setup combining Claude Code with specialized domain agents, parallel code review, and self-improving knowledge systems.
3/18/2026
We optimized Dash's relevance judge with DSPy
Dropbox optimized their relevance judge using DSPy for Dash, improving ranking and evaluation across multiple ML pipelines at scale.
3/18/2026
TrustAgentAI – Cryptographic receipts for MCP tool calls (non-repudiation layer)
TrustAgentAI is an open-source accountability layer adding cryptographic receipts and non-repudiation to MCP tool calls for AI agents.
3/18/2026
Gas Town by Kilo
Gas Town is Steve Yegge's agent orchestrator coordinating multiple AI coding agents simultaneously, hosted on Kilo Cloud infrastructure.
3/18/2026
Neural-Symbolic Logic Query Answering in Non-Euclidean Space
HYQNET is a neural-symbolic model that answers complex first-order logic queries on knowledge graphs by integrating interpretability with generalization.
3/18/2026
NextMem: Towards Latent Factual Memory for LLM-based Agents
NextMem proposes a latent factual memory framework for LLM-based agents to address limitations of existing textual and parametric memory approaches.