I gave my AI agent database access. Then I built a firewall so it couldn't wipe prod.

A few months ago I gave an autonomous agent write access to a real database. It was a LangChain-style loop — plan, call a tool, observe, repeat and one of the tools ran SQL. It worked great in the demo. Then I watched it, during a "clean up the test rows" task, generate this: sql DROP TABLE users; I

Related Stories

📰

You don't need NextJS: here's why

📰

Streamlining Cloud Infrastructure with Custom Symfony Packages

The Scaling Laws That Made LLMs Work

Building LSTMs with PyTorch and Lightning AI Part 3: Finishing the LSTM Cell