ampdot

Researchers and writers can apply for proxy access to the GPT-3.5 base model (code-davinci-002)

AI safety researchers and creative writers can apply for proxied access to the GPT-3.5 base model through, also known as code-davinci-002. Publicly available base models include "davinci-002" (the text-davinci-xxx models are not base models) and cohere's "xlarge" model. I recommend interacting with language models using janus' loom. One such implementation...

Dec 1, 202314

ampdot

ampdot

Queuing theory: Benefits of operating at 60% capacity

Researchers and writers can apply for proxy access to the GPT-3.5 base model (code-davinci-002)

Signals of Slop: How to identify and avoid creating slop

ampdot's Shortform

ampdot

Queuing theory: Benefits of operating at 60% capacity

Researchers and writers can apply for proxy access to the GPT-3.5 base model (code-davinci-002)

Signals of Slop: How to identify and avoid creating slop

ampdot's Shortform

Signals of Slop: How to identify and avoid creating slop

ampdot's Shortform

Queuing theory: Benefits of operating at 60% capacity

Researchers and writers can apply for proxy access to the GPT-3.5 base model (code-davinci-002)