[catalypso]

I just tried it and I'm actually surprised with how well they work even with base64 encoded inputs.

This is assuming they don't call an external pre-processing decoding tool.

[simonw]

The LLM UIs that integrate that kind of thing all have visible indicators when it's happening - in ChatGPT you would see it say "Analyzing..." while it ran Python code, and in Claude you would see the same message while it used JavaScript (in your browser) instead.

If you didn't see the "analyzing" message then no external tool was called.