Lovre

Message

218

The Dark Arts of Tokenization or: How I learned to start worrying and love LLMs' undecoded outputs

Introduction There are 208 ways to output the text ▁LessWrong[1] with the Llama 3 tokenizer, but even if you were to work with Llama 3 for thousands of hours, you would be unlikely to see any but one. An example that generalizes quite widely: if you prompt Llama 3.2 3B...

Oct 17, 202542

Putting multimodal LLMs to the Tetris test

(See this X (Twitter) thread for a much shorter version of this post.) Introduction With the advent of vision abilities in LLMs, a virtually limitless vista has opened in the realm of their evaluations: they can now be tested on any task that requires vision and has a ~finite input/action...

Feb 1, 202430

Who models the models that model models? An exploration of GPT-3's in-context model fitting ability

Introduction Much has been written and much has been observed about the abilities of GPT-3 on many tasks. Most of these capabilities, though not all, pertain to writing convincing text, but, not to undermine GPT-3's impressiveness at performing these tasks, we might call this the predictable part of its oeuvre....

Jun 7, 2022112

LESSWRONG
LW

LESSWRONG
LW

Lovre

Lovre

Lovre

Lovre

The Dark Arts of Tokenization or: How I learned to start worrying and love LLMs' undecoded outputs

Putting multimodal LLMs to the Tetris test

Who models the models that model models? An exploration of GPT-3's in-context model fitting ability

The Dark Arts of Tokenization or: How I learned to start worrying and love LLMs' undecoded outputs

Putting multimodal LLMs to the Tetris test

Who models the models that model models? An exploration of GPT-3's in-context model fitting ability