• your topics
• add yours

Braid: Bounded reasoning for LLMs using symbolic Mermaid graphs

2025 LLM Year in Review (Andrej Karpathy)

LLM Year in Review

CAD: Disaggregating Core Attention for Efficient Long-Context LLM Training

Building an LLM evaluation framework: best practices

Show HN: AI Audience Platform for Practicing Public Speaking

AI's Unpaid Debt: How LLM Scrapers Destroy the Social Contract of Open Source

Show HN: Open-Source Browser Use LLM (30B, A3B)

CTO bench: an online LLM coding benchmark

Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude)

Training and Evaluating LLMs as General-Purpose Activation Explainers

Show HN: RunMesh – OpenAI-first TypeScript framework for agentic applications

Show HN: LiteEvo – Let LLMs evolve their own playbook based on trial and error