Hacker News Reader

Hey HN! back again presenting a 2-in-1:

- a longform take on Code Interpreter, starting with a summary, but then tying it in to the recent history exploring inference-time improvements for LLMs (inspired by Libratus/Cicero/Voyager)

- a podcast discussion with Simon Willison, Alex Volkov, and others sharing tips and tricks and discoveries on Code Interpreter.

enjoy and please let me know if any questions!

View on HN

Thanks for asking me to hop on a space together @swyx

I didn't imagine so many folks will tune-in, share their use-cases of these new superpowers, share limitations, explore the boundaries (no more running binaries) and then explore the jailbreaks (apparently binaries are still possible to run w/ some tricks!) and more!

Incredibly deep recap as well

Reply on news.ycombinator.com