Stop Telling Your AI It's an Expert: Here's What to Do Instead
USC researchers found that persona prompting ('You are an expert') hurts factual accuracy while helping style tasks. Here's the data and what to do instead.
AIPromptingResearch
Writing about AI tooling, infrastructure, and the security gaps nobody is talking about.
Stop Telling Your AI It's an Expert: Here's What to Do Instead
USC researchers found that persona prompting ('You are an expert') hurts factual accuracy while helping style tasks. Here's the data and what to do instead.
How the YC CEO Structured an AI Engineering Workflow: What You Can Learn From It
Garry Tan open-sourced 28 Claude Code skills that simulate a virtual engineering team. The interesting part isn't the skills, it's the pipeline structure. Here's the pattern you can steal.
Two Papers That Should Change How Your Team Uses AI Coding Tools
One paper shows 75% of AI agents break working code during maintenance. The other shows copy-pasting 7 layers in an old model topped the leaderboard. Together they say: we're building faster than we understand.
What AI Agent Adoption Actually Looks Like: China's OpenClaw Craze
OpenClaw surpassed React as GitHub's most-starred project. In China it became a cultural phenomenon, then got banned from government devices. 20% of its skills were malicious. Here's what enterprise teams should learn.
Your Security Scanner Got Hacked: The TeamPCP Supply Chain Attack
A single threat actor compromised Trivy, Checkmarx, and LiteLLM in one week. Two of the three targets were security scanners. Here's what happened and what to do about it.
Anthropic Accuses DeepSeek and Others of Distillation Attacks on Claude
Anthropic reveals industrial-scale distillation attacks by three Chinese AI labs, creating 24,000+ fraudulent accounts and 16 million exchanges to extract Claude's capabilities.
LLM Concept Vectors: MIT/UC San Diego Research on Steering Model Behaviour
Researchers extract 'concept vectors' from LLMs, enabling runtime behavior tuning without retraining. Under a minute on a single GPU, fewer than 500 examples.
vLLM v0.16.0: Throughput Scheduling and a WebSocket Realtime API
vLLM v0.16.0 adds a WebSocket Realtime API for voice-enabled agents, async scheduling for higher throughput, and speculative decoding improvements.
Chandra OCR: The New Gold Standard in Open-Source Document Parsing
Datalab's Chandra OCR scores 83.1% on the olmOCR benchmark, beating GPT-4o and Gemini. Full-page decoding with layout-aware output in Markdown, HTML, or JSON.
Request Hedging: Accelerate Your App by Firing Duplicate Requests
Request hedging fires a second duplicate request after a short delay, racing to beat outlier latency. Google cut P99.9 latency by 96% with just 2% extra traffic.
Understanding Vectors, Embeddings, and RAG for Smarter Search
A practical guide to vector search, embeddings, similarity metrics, vector indexes, and Retrieval-Augmented Generation (RAG) for developers building semantic search systems.