Hacker News Reader

It could be argued that "thinking" / CoT in latent space abstracts away the language issue, and that in fact language in reasoning steps doesn't matter. Latent tokens could actually be decoded afterwards to any target language. Much more powerful IMO.

On a side note, there's decent research on how well bilingual humans do actually think in both language, and are actually better at decisive thinking outside of their mother tongue.

View on HN

I think another argument is that the CoT is simply unrolling the recurrent loop that this method uses, and doing an unembedding -> embedding -> unembedding during the decoding process.

So at best, using a recurrent loop is only saving you from doing the embedding -> unembedding at each token which is relatively small compared with the height of the decoder blocks.

Reply on news.ycombinator.com