Next-Latent Prediction Transformers Learn Compact World Models — mentioned by jlhawn

Mon, 12 Oct 2026 17:52:07 GMT

> LLMs are powerful autocomplete with vast and broad memory, they do not think. This is really only true insofar as they are designed such that they output language tokens and their intermediate "chain of thought" is also done in language tokens, but now that's really only done for auditability. There are much more abstract layers before the model output layer of a single token prediciton and they could be designed to to "think" using these more abstract layers as intermediates instead like how many people think in concepts rather than words. There are even some research models on this (see…

Paper and discussion history. A mention is not an endorsement.

Next-Latent Prediction Transformers Learn Compact World Models — HN submission

Wed, 17 Jun 2026 11:28:06 GMT

Next-Latent Prediction Transformers Learn Compact World Models (2025)

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Next-Latent Prediction Transformers Learn Compact World Models · HackerPapers discussions

Next-Latent Prediction Transformers Learn Compact World Models — mentioned by jlhawn

Next-Latent Prediction Transformers Learn Compact World Models — HN submission