It's also literally factually incorrect. Pretty much the entire field of mechanistic interpretability would obviously point out that models have an internal definition of what a bug is.
> Thus, we concluded that 1M/1013764 represents a broad variety of errors in code.
(Also the section after "We find three different safety-relevant code features: an unsafe code feature 1M/570621 which activates on security vulnerabilities, a code error feature 1M/1013764 which activates on bugs and exceptions")
This feature fires on actual bugs; it's not just a model pattern matching saying "what a bug hunter may say next".
It's also literally factually incorrect. Pretty much the entire field of mechanistic interpretability would obviously point out that models have an internal definition of what a bug is.
Here's the most approachable paper that shows a real model (Claude 3 Sonnet) clearly having an internal representation of bugs in code: https://transformer-circuits.pub/2024/scaling-monosemanticit...
Read the entire section around this quote:
> Thus, we concluded that 1M/1013764 represents a broad variety of errors in code.
(Also the section after "We find three different safety-relevant code features: an unsafe code feature 1M/570621 which activates on security vulnerabilities, a code error feature 1M/1013764 which activates on bugs and exceptions")
This feature fires on actual bugs; it's not just a model pattern matching saying "what a bug hunter may say next".