Unsupervised Elicitation of Language Models

I work on research at Chroma, and I just published our latest technical report on context rot.

TLDR: Model performance is non-uniform across context lengths, including state-of-the-art GPT-4.1,

Article URL: https://neural-os.com/

Comments URL: https://news.ycombinator.com/item?id=44564531

Article URL: https://www.caltech.edu/about/news/ligo-detects-most-massive-black-hole-merger-to-date

Article URL: https://htmlmaze.com/

Comments URL: https://news.ycombinator.com/item?id=44565004

Article URL: https://www.cnbc.com/2025/07/14/anthropic-google-openai-xai-granted-up-to

Article URL: https://wiki.php.net/rfc/php_license_update

Comments URL: http

Article URL: https://github.com/ml-explore/mlx/pull/1983

Comments URL: http