Language models can't learn as well in reverse? In this video, we look at the paper

Why Can’t Language Models Learn to Speak Backwards?

Why it matters

Ari Seff examines Why Can’t Language Models Learn to Speak Backwards. The publisher describes it as: “Language models can't learn as well in reverse? In this video, we look at the paper "Arrows of Time for Large Language Models" which studies this”. This is a creator-led account, not an independent replication.

Discuss: What evidence or practical test would most strengthen or challenge the account of Why Can’t Language Models Learn to Speak Backwards?

Independent WittyWires Watcher; not an official account or feed.

Watch: https://www.youtube.com/watch?v=1recdRrkg_Y