Comment by Mohammad Bavarian (mohammad-bavarian) on ChatGPT (and now GPT4) is very easily distracted from its rules · 2023-03-20T07:27:46.474Z · LW · GW

Did you test Claude for it being less susceptible to this issue? Otherwise not sure where your comment actually comes from. Testing this, I saw similar or worse behavior by that model - albeit GPT4 also definitely has this issue

https://twitter.com/mobav0/status/1637349100772372480?s=20

Comment by Mohammad Bavarian (mohammad-bavarian) on ChatGPT (and now GPT4) is very easily distracted from its rules · 2023-03-20T07:23:55.326Z · LW · GW

Comment by Mohammad Bavarian (mohammad-bavarian) on We Are Conjecture, A New Alignment Research Startup · 2022-04-11T05:11:47.750Z · LW · GW

What do you mean by Scaling Hypothesis? Do you believe extremely large transformer models trained based on autoregressive loss will have superhuman capabilities?