Comment by Theresa Barton (theresa-barton) on Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs · 2025-02-25T19:44:04.685Z · LW · GW

Hi! Did you try this technique on any other LLMs? Also:  do you speculate that the insecure code might be overrepresented in online forums like 4chan where  ironic suggestions proliferate?

Comment by Theresa Barton (theresa-barton) on GPT-4 · 2023-03-22T18:23:57.158Z · LW · GW

I think performance on AP english might be a quirk of how they dealt with dataset contamination. English and Literature exams showed anomalous amount of contamination (lots of the famous texts are online and referenced elsewhere) so they threw out most of the questions, leading to a null conclusion about performance.