AI brief
Researchers introduce the J++ Lens, an improvement to the J-Lens method for reading verbalisable representations from language model activations.
Written by AI from LessWrong's published text.
Background
From our own funding, model and news trackers, not from the source.
Anthropic
- Latest funding
- Growth · $65B · 28 May 2026
- Newest model on the API
- Claude Haiku 5.5 · 7 Oct 2026 · $0.1 in / $0.5 out per million tokens
Source
“Kola Ayonrinde, Anthropic Fellows, koayon@gmail.com ; Jack Lindsey, Anthropic TL;DR : The J-Lens was proposed to read verbalisable representations from language model activations.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗