Mmastodon TechnologyTechnology first seen 12 h ago, last 12 h ago, peak #3
Retrofitting language models to operate directly on bytes
Original: Retrofitting language models to operate over bytes https://www.nature.com/articles/s41586-026-11111-4 # HackerNews # Tec
A new Nature paper describes an approach to retrofit language models so they can operate directly over bytes rather than fixed token vocabularies. The work could simplify how models handle text in any language, code, or unusual input, avoiding tokenization pitfalls. Discussion is spreading among AI researchers and developers weighing the practical implications for future model architectures.
Why now: A high-profile Nature publication on a fundamental AI architecture change is drawing attention from the machine learning community.
Evidence
- Retrofitting language models to operate over bytes https://www.nature.com/articles/s41586-026-11111-4 # HackerNews # Tech # AI · hackernews@robot.villas · 2
API: https://socialmediatrends-api.osmike.com/v1/trends/1805989