Context Language Models · HackerPapers discussions

Context Language Models — mentioned by lurker137

Mon, 26 Oct 2026 04:37:08 GMT

This is why I think the next evolution will be giving models full control of their own context, where they can edit it just like a file. This idea was in a recent paper, where models could even be specifically trained for context management [1]. For the problem of the prefix cache being invalidated, they thought of implementing a suffix cache [1]: https://arxiv.org/abs/2609.37725

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

Context Language Models — HN submission

Thu, 01 Oct 2026 14:51:33 GMT

Context Language Models

178 points; 52 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Context Language Models — mentioned by tomatomatomato

Wed, 30 Sep 2026 13:18:24 GMT

The Bitter Lesson for context management: Giving LMs unrestricted control over their context beats human-designed SOTA! Introducing Context Language Models (CLMs) - Natively manage their own context - Treat context as a file - Learn policies in CLM weights, no harness Check out our paper, code, and play with CLM! Paper: arxiv.org/abs/2609.37725 Code: github.com/facebookresearch/context-language-models HF paper: huggingface.co/papers/2609.37725

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

Context Language Models — HN submission

Wed, 30 Sep 2026 13:18:24 GMT

Context Language Models

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