# The Context Layer

> Technical writing.

Every post is available as plain Markdown by appending `.md` to its URL. The full text of all posts is at https://dperez.com/llms-full.txt.

## Posts

- [Who Owns What Your Agent Learns](https://dperez.com/posts/who-owns-what-your-agent-learns.md): Agents that learn from their own work are already in production. Whether that learning lives in the model's weights or in the harness around it decides who can inspect, revert and keep it.
- [PHP2Shell: When Finding Bugs Gets Faster Than Fixing Them](https://dperez.com/posts/php2shell.md): AI helped find PHP2Shell, though less than the headlines imply. The sharper lesson is what happens when bugs get cheaper to find and fixing them stays slow.
- [The Bottleneck Moved to the Merge](https://dperez.com/posts/the-bottleneck-moved-to-the-merge.md): Coding agents can produce code faster than an organisation can absorb it. Source control, review and CI each break differently, and Anthropic's Scion shows the order.
- [Build for the Model You Trust Least](https://dperez.com/posts/build-for-the-model-you-trust-least.md): Satya Nadella argues enterprises should treat frontier models as insider risks. That moves the hard engineering into the system around the model, where a 1972 security idea still applies.
- [The Agent Just Stopped Living in the Chat Window](https://dperez.com/posts/the-agent-just-stopped-living-in-the-chat-window.md): Meta put an agentic model on a single consumer GPU, while xAI and OpenAI gave their agents computers in the cloud. Neither yet gives enterprises an agent identity they can govern.

## Optional

- [RSS feed](https://dperez.com/rss.xml)
- [Sitemap](https://dperez.com/sitemap-index.xml)