Anthropic locked Claude Mythos behind a $100M vetted-access program. Meanwhile, DeepSeek V4 is on Hugging Face for anyone to download. The policy and the threat model point in different directions.
Running Claude Code out of the box is leaving a lot on the table. Here's the exact setup I use: Opus 4.7, extended thinking, 1M context, and a hook that makes every prompt leaner before it hits the model.
Claude 4.7 and the End of Prompt Engineering as We Knew It
The era of bag-of-tricks prompts is closing. The new bottleneck isn't writing the perfect sentence. It's engineering the right context. Notes from a year of building with agentic models.
