Alejandro Tlaie

Karma: 43

A short project on Mamba: grokking & interpretability

Alejandro Tlaie18 Oct 2024 16:59 UTC

21 points

0 comments6 min readLW link

Toy Models of Superposition: what about BitNets?

Alejandro Tlaie8 Aug 2024 16:29 UTC

5 points

1 comment5 min readLW link

On predictability, chaos and AIs that don’t game our goals

Alejandro Tlaie15 Jul 2024 17:16 UTC

4 points

8 comments6 min readLW link

Introducing SARA: a new activation steering technique

Alejandro Tlaie9 Jun 2024 15:33 UTC

17 points

7 comments6 min readLW link