News for hackers. Stuff that matters.

A comment on Things we learned about LLMs in 2024. Parent comment

Re:Things we learned about LLMs in 2024 by catalypso on Wednesday January 01, 2025 @02:08PM (#42568351)
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.

[ Parent | on HN ]
Re:Things we learned about LLMs in 2024 by simonw on Wednesday January 01, 2025 @02:17PM (#42568445)
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.

[ Parent | on HN ]