GENERATIVE AI

→ View original post on X — @thatroblennon

Reactor Migration to Claude Opus 3: Triple Cost for Triple Quality

By

@thatroblennon

–

23 April 2024 3h28

When we moved Reactor to Claude Opus 3 our costs tripled but so did the quality of the outputs

LLaMA 3 Context Window Doubled to 16K Tokens Open-Source

By

–

23 April 2024 3h10

I've doubled LLaMA 3's context window to 16K tokens. Fully open-source. Link in thread:

LLaMA 3 Context Window Extended to 16K Tokens Open-Source

By

–

23 April 2024 3h09

I've doubled LLaMA 3's context window to 16K tokens. Fully open-source. Link in thread:

LLaMA 3 Context Window Doubled to 16K Tokens

By

–

23 April 2024 3h09

I've doubled LLaMA 3's context window to 16K tokens. Fully open-source. Link in thread:

LLaMA 3 Context Window Doubled to 16K Tokens

By

–

23 April 2024 3h07

I've doubled LLaMA 3's context window to 16K tokens. Fully open-source. Link in thread:

→ View original post on X — @karpathy

LLMs as Arrays: Meditation on Entropy and Truth

By

@karpathy

–

23 April 2024 3h00

As I emerged from meditation it dawned on me that LLMs are just one array of floats and a while loop over some super simple arithmetic on its elements. It is entropy that is the root of suffering. It's by deleting the superfluous that we uncover truth. And thus I was enlightened.