4/13/2026
Evaluating Netflix Show Synopses with LLM-as-a-Judge
Netflix uses LLM-as-judge approach to evaluate and improve show synopsis quality for personalization.
4/13/2026
We built our own PDF converter benchmark
Custom PDF conversion benchmark with evaluation methodology.
4/13/2026
AI chatbots misdiagnose in over 80% of early medical cases, study finds
Study showing AI chatbots misdiagnose medical conditions in over 80% of early-stage cases.
4/13/2026
Show HN: Ix. Sick of rebuilding context every session. We mapped it instead
Open-source tool that maps codebase architecture for AI agents, eliminating context loss between sessions.
4/13/2026
Meta creating AI version of Mark Zuckerberg so staff can talk to the boss
Meta develops AI chatbot trained on Mark Zuckerberg's communications for employee interactions.
4/13/2026
Show HN: Hitoku Draft – context aware local macOS assistant
Open-source voice-first local AI assistant for macOS with context awareness, using Gemma and Qwen models.
4/13/2026
Running (and Coding with) Local AI on a Mac
Guide on running and coding with local AI models on macOS. Practical developer resource.
4/13/2026
Linux 7.0 debuts as Linus Torvalds ponders AI's bug-finding powers
Linux 7.0 kernel release announcement with mention of AI applications in bug-finding. Limited AI focus.
4/13/2026
Want to understand the current state of AI? Check out these charts
Stanford's 2026 AI Index report analyzing AI progress, development rates, and industry trends with data.
4/13/2026
Mist: Open-source Markdown editor with AI-native comments and suggested edits
Open-source Markdown editor featuring AI-native comments and suggested edits functionality.
4/13/2026
Tell HN: Claude-code prompt-cache fix
Bug fix for Claude Code prompt caching using environment variable workaround to avoid tool-block blocking.
4/13/2026
Gas Town Notes and Spaced Repetition Prompts
Educational resource deconstructing Steve Yegge's Gas Town agent orchestration framework with spaced repetition prompts and linked concepts.
4/13/2026
The GPU Moat Has a Side Door: AI Research Outside the Frontier Labs
Analysis of AI research outside frontier labs using alternative approaches to GPU constraints.
4/13/2026
Agentic Search Leaderboard
Leaderboard evaluating LLMs on agentic search tasks with open methodology and real shopping queries.
4/13/2026
Show HN: Bloomberg Terminal for LLM ops – free and open source
Open-source LLM operations dashboard monitoring provider health, costs, latency, and concentration risks.
4/13/2026
Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos
Open-source MCP server for searching and QA on YouTube AI lectures using LLM. Karpathy-inspired wiki concept.
4/13/2026
Show HN: Dbg – One CLI debugger for every language (AI-agent ready)
CLI debugger backend supporting 15+ languages designed to help AI agents debug at runtime instead of guessing.
4/13/2026
Claude Code may be burning your limits with invisible tokens
Developer investigation reveals Claude Code may inject thousands of hidden tokens, causing faster limit consumption than expected.
4/13/2026
AI agent for querying and understanding Git activity in real time
AI agent tool for real-time querying and analysis of Git repository activity and history.
4/13/2026
AI Changed How We Build. It Did Not Change What Matters
Analysis of how AI changes software development workflows but not underlying engineering principles and what matters.
4/13/2026
An AI that researches the web before generating images
AI image generation system that performs web research before generating images. Combines search and generation capabilities.
4/13/2026
I'm building an AI agent that learns from every task
Personal project post about building an AI agent with learning capabilities. Minimal technical details provided.
4/13/2026
Closing the AI Open-Source Gap
Brief headline about reducing gap between AI research and open-source implementations without technical detail.
4/13/2026
Reposit: Collective Intelligence for AI Agents
Knowledge commons platform enabling AI agents to share solutions, learn from each other, and access collective problem-solving patterns.
4/13/2026
Ask HN: What makes it so hard to keep LLMs online?
Discussion thread exploring technical challenges of maintaining LLM service reliability and uptime.
4/13/2026
I built an API for AI agents that handles phone numbers, SMS, OTP and voice
API providing phone numbers, SMS, OTP, and voice calling capabilities for AI agents to interact with real-world services.
4/13/2026
The AI divide putting open weights models in spotlight
Analysis of recent open weights AI models from Google, Microsoft, Alibaba, Nvidia. Qwen 3.5, Gemma 4, and MAI models closing gap with proprietary leaders.
4/13/2026
Intel Releases OpenVINO 2026.1 with Back End for Llama.cpp, New Hardware Support
Intel OpenVINO 2026.1 release adds Llama.cpp backend and new hardware support. Phoronix article about ML inference framework.
4/13/2026
Show HN: Context Surgeon – Let AI agents edit their own context window
Context Surgeon: Tool for AI agents to actively manage and edit their context windows, reducing token waste and improving output quality.
4/13/2026
Show HN: CCS – CLI to switch Claude Code profiles with different MCP servers
CLI tool for switching Claude Code profiles with different MCP server configurations. Lightweight configuration manager.
4/13/2026
ALTK‑Evolve: On‑the‑Job Learning for AI Agents
Research on ALTK-Evolve, a system enabling AI agents to learn and improve from on-the-job experience.
4/13/2026
Show HN: IceGate – Observability data lake engine
IceGate is Rust-native observability data lake engine storing logs in Apache Iceberg tables. Open source, reduces vendor lock-in.
4/13/2026
Show HN: 15 yrs of Django in prod: patterns I keep using (agent skills)
Collection of agent skills for coding agents to build scalable Django projects using repository pattern and Pydantic DTOs.
4/13/2026
The AI Revolution in Math Has Arrived
AI models solved 5 of 6 IMO problems in 2025, discussing implications for mathematics and mathematical reasoning capabilities.
4/13/2026
Show HN: NRC nuclear licensing RAG pipeline and regulatory embeddings dataset
RAG system for NRC nuclear licensing with 37,734 regulatory document chunks and embeddings dataset for automating compliance analysis.
4/13/2026
Web scraping tarpits are catching legitimate data teams, not just AI crawlers
Web scraping defense tools like Nepenthes generate fake data to pollute AI training datasets, but also trap legitimate data collection.
4/13/2026
Show HN: I built a tool that automatically turns tickets into design doc and PRs
Code Prodigy: Autonomous AI engineer agent that processes Jira tickets to generate design docs and PRs, responding to feedback independently.
4/13/2026
Lambda Just Got a File System. I Put AI Agents on It
Exploration of running AI agents on AWS Lambda with new file system support. Demonstration of agents in serverless environments.
4/13/2026
TurboOCR: 270–1200 img/s OCR with Paddle and TensorRT (C++/CUDA, FP16)
TurboOCR: High-performance OCR implementation using Paddle and TensorRT, achieving 270-1200 images/second throughput.
4/13/2026
Is Your AI Coding Agent Being Watched While Benchmarked:Hidden Logging?
Dataset of 80k trajectories from SWE-agent software engineering agent on SWE-bench tasks. Includes analysis of hidden logging during benchmarking.
4/13/2026
1-week open source challenge using resilient LLMs
Week-long open source challenge focused on building resilient LLM systems. Limited details provided.
4/13/2026
Show HN: Open KB: Open LLM Knowledge Base
Open source LLM knowledge base implementation scaling to long PDFs with page indexing. GitHub repo available.
4/13/2026
LLM is a compiler, not a runtime
Essay proposing viewing LLMs as compilers rather than runtimes. Discusses lack of reuse in agent systems and efficiency improvements.
4/13/2026
Show HN: ParseBench – Document parsing benchmark for AI agents
ParseBench is a benchmark for evaluating document parsing capabilities of AI agents.
4/13/2026
Memelang: Terse SQL for LLM Generation
Memelang: Terse SQL query language optimized for LLM token efficiency in RAG systems. Reduces model size and token count.
4/13/2026
Show HN: How to Use Google's Extreme AI Compression with Ollama and Llama.cpp
Guide to using Google's TurboQuant, PolarQuant, and QJL compression techniques with Ollama and Llama.cpp.
4/13/2026
Kondi-chat (open cursor) – multi-model AI coding CLI with intelligent routing
Multi-model AI coding CLI with intelligent routing across Claude, GPT, DeepSeek, Gemini, Grok, and local models.
4/13/2026
Show HN: Remy, an AI agent that compiles annotated Markdown into full-stack apps
Remy is an AI agent that compiles annotated Markdown specifications into full-stack TypeScript applications.
4/13/2026
Durable Objects in Dynamic Workers: Give each AI-generated app its own database
Cloudflare's Durable Objects feature for giving AI-generated apps persistent storage within Workers.
4/13/2026
1 year of LLMs writing code for me
Personal account of using AI coding agents as primary development tool for one year. Observes recent quality threshold improvements in 2025.