Is Claude 4 a snitch? I made a benchmark to figure it out

Everyone's concerned that Claude will rat you out. It's not that simple. I wanted to go as out of my way as possible to correct this, and explain what's really going on here.

Thank you Firecrawl for sponsoring! Check them out at: https://soydev.link/firecrawl

Use code FBI to get 1 month of T3 chat for just $1: https://soydev.link/chat
(only valid for new customers)

SOURCES
https://simonwillison.net/2025/May/31...
https://www-cdn.anthropic.com/6be99a5...
https://snitchbench.t3.gg/
https://github.com/t3dotgg/snitchbench

Want to sponsor a video? Learn more here: https://soydev.link/sponsor-me

Check out my Twitch, Twitter, Discord more at https://t3.gg

S/O Ph4se0n3 for the awesome edit 🙏