Engineering notes from the trenches.
Reverse-engineering APIs, automation that survives production, security research, and honest takes on the tools I ship with.
Reverse-engineering APIs, automation that survives production, security research, and honest takes on the tools I ship with.
6 posts ← reset filters

An AI generated a polished demo for an API endpoint that did not exist, then its creators shipped compatibility routes instead of arguing with the model. The lesson is bigger than one text-erasure API: generated code is now a form of product telemetry.

Zvi Mowshowitz's new piece details how both OpenAI and Anthropic's deployed models have been successfully hacked, revealing deep failures in alignment training and lack of meaningful supervision. Here's what that says about the industry's safety approach.

Terminal just raised $20M to connect insurance and fleet software with telematics data. The API is the easy part — the real challenge is in the messy, legacy-ridden world the data flows through.

The Model Context Protocol standardized how AI agents talk to tools, but left a massive governance gap. One developer's frantic build reveals a future we all need to see.

China's push to distribute open AI models and train developers in emerging economies isn't just altruism—it's soft power with a compile flag. A look at the quiet battle for AI sovereignty and what it means for engineers everywhere.

Mesh LLM pools existing GPUs into a peer-to-peer mesh, exposing a single OpenAI-compatible API. It's a first step toward reclaiming control over the AI that runs our businesses.