The Inverse Scaling Effect on Language Models

In inverse scaling on tasks like this because the smaller models kind of answer randomly they're not very good at answering the questions at all. Another another good one was the quote repetition which shows that if you present a language model with a series of sentences and ask it to repeat them. The final third prize winner from the first round was called hindsight neglect. And in each case you make the actual outcome line up with the expected value so if the expected value is positive and it seems like a good idea to take the bet then it went well, according to our results.