AI Radar
Other people's articles on AI agents, LLMs and AI-assisted development. I read what comes through and keep what's worth your time.
- · generativeai.pub
His entire AI skills library loads in 660 tokens.
Discover strategies to minimize token consumption in AI agent skills using Matt Pocock’s techniques like leading words, progressive disclosure, and modular invocation patterns.
- · generativeai.pub
Jev Doesn’t Talk. It Answers. Why a Model With No Text Output Might Matter More Than GPT-6
Explore TypeSafe's Jev model, which outputs calibrated probabilities instead of text. Learn about its API structure, cost efficiency compared to GPT-6, and the implications of RLCD training for automated decision-making systems.
- · claude.dev
Getting the Most Out of Opus 5.5 in Claude and Claude Code
Learn to prompt Opus 5.5 effectively for coding tasks, configure CLAUDE.md for long runs, manage subagents, and handle security flags in Claude Code.
- · coinbase.com
Interviewing Engineers in the AI Era: Lessons from a Year of Rebuilding
Learn how Coinbase redesigned its engineering interview loop to assess AI fluency instead of pattern recall, focusing on directing models and evaluating output.
- · generativeai.pub
4 Steps To Optimize Claude Token Usage
Learn four practical strategies to reduce AI coding costs including code indexing, output compression, session management, and model selection techniques for better token efficiency.
- · generativeai.pub
Skills vs. MCP vs. RAG vs. Memory: How to Actually Give AI Agents the Knowledge They Need
Distinguish between skills, MCP, RAG, and memory to optimize AI agent knowledge retrieval. Avoid context bloat and learn when to apply each strategy for accurate task resolution.
- · gruhn.me
Don't be a meat proxy
Learn why blindly forwarding AI responses in Slack or code reviews reduces value. Discover how to validate and rewrite AI output to maintain human agency and improve team communication efficiency.
- · newsletter.posthog.com
This post will save you tokens
Explore proven techniques for reducing LLM expenses via improved caching strategies, model routing, context engineering, and observability practices implemented at scale.
- · newsletter.posthog.com
Read this before deleting your AGENTS.md
Reduce AI agent context bloat instead of adding rules. Explore three strategies: automated health checks, testing context like code, and feedback loops for improved model performance.
- · f2r.github.io
I Stopped Running Several Agents
Why running multiple AI coding agents creates bottlenecks and decision fatigue. Optimize workflow by limiting work in progress and elevating human capacity instead of forcing parallelism.