Discussion (3 Comments)Read Original on HackerNews

jatins•11 minutes ago

All the signs of slop, short one line paragraphs.

Tested a passage on Pangram and 100% AI generated btw https://www.pangram.com/history/f6b20d8e-4eb4-4bc2-b325-ad39...

argee•about 2 hours ago

Is the model "thinking of the last word for the next line already" or is "the word that came last in the second line was already showing high p from considering only the first line"? Shouldn't we care about such a distinction?

usernotfoundrn•about 1 hour ago

If “aim” is already highly probable after the first line, the example is much less interesting.

A more cool question is whether the model is carrying a latent representation of the destination that isn’t yet reflected in the immediate token probabilities?

I don’t know. Anthropic is investigating: https://www.anthropic.com/research/tracing-thoughts-language...

My Throw Decides My Aim

⚡ Community Insights

Discussion (3 Comments)Read Original on HackerNews