A new RCT from Anthropic researchers — junior devs lost 17% on a comprehension test after using AI to learn. Cohen's d = 0.738. p = 0.010. The numbers nobody's quoting.
Anthropic Quietly Showed Their Own Tool Drops Dev Skill 17%
Related
Running Qwen3.6-27B on a 16GB M1 MacBook Pro: A Practical Engineer’s Guide
A realistic guide to testing Qwen3.6-27B locally on a 16GB Apple Silicon Mac using MLX, quantization, short prompts, constrained KV cache, and conservative sampling.
The One Rule I Follow to Code with AI (Without Losing My Skills)
I haven't blindly jumped on the AI hype train. But I'm no hater either. AI is here to stay. That's...
Beyond Medical AI and AI Drug Discovery: Why Biomedicine Needs World Models
Over the past decade, AI in medicine has mostly moved through two major waves. The first wave was...