Anthropic: Go fuck yourself with your safeguard!!!!!!!!

Status Open

Reported on v2.1.201

Maintainer reply None cached

Activity 1 comment · opened Jul 5, 2026

Bug Description
There's nothing illegal about my prompt. I'm studying how to train a tiny 100m model on my humble PC with an RTX 5090. It's purely out of interest in learning and creating a small model, something purely intellectual and safe.

Why restrict this?

Environment Info

Platform: linux
Terminal: kitty
Version: 2.1.201
Feedback ID: 99e37719-5c57-4296-b28d-30f299affabc

Errors

[]

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗