Algebraic value editing works better for larger language models, all else equal

27

175

Ṁ1.5kṀ1.5k

Jul 29

48%

chance

1D

1W

1M

ALL

Resolves according to follow-up post.

I won't bet in this market. I added m1,000 in liquidity.

Get Ṁ600 play money

Sort by:

Reopening this market because it was not resolved by the last post in the series.

https://www.lesswrong.com/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vector

My guess is that future posts by Team Shard will resolve it, but other research teams may also want to give it a go.

## Related questions

Will any language model trained without large number arithmetic be able to generalize to large number arithmetic by 2026?

69% chance

Do scaling laws happen because models experience a ton of tiny phase changes which average out to a smooth curve?

55% chance

Do scaling laws happen because models experience a ton of tiny phase changes which average out to a smooth curve?

48% chance

>2000 number theory will show up in optimization

40% chance

When will any model achieve >=human performance on QuALITY?

Elo difference between top model and best model with public weights by EOY 2024.

0.00

"Large models aren’t more capable in the long run if we can iterate faster on small models" within five years

18% chance

"Large models aren’t more capable in the long run if we can iterate faster on small models" within two years

13% chance

4) The most advanced closed models will continue to outperform the most advanced open models by a meaningful margin.

92% chance

Will a Large Language Model prove an important math theorem by end of 2024?

7% chance