From 4c509e5703e6cfb6a7a853980d896d552722b1eb Mon Sep 17 00:00:00 2001 From: CaptainJack2491 Date: Mon, 10 Aug 2026 19:10:00 +0100 Subject: Add link to published J-space writeup (jayrup.me/blog/jacobian-lens-frequency) --- README.md | 3 ++- anthropic-j-space.md | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 4af7cc2..f9ad0cf 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,8 @@ mechanisms. - `fundamental-questions.md` — Five open questions nobody can answer about how LLMs work. These are the compass. - `anthropic-j-space.md` — Summary of Anthropic's July 2026 paper on - the global workspace / J-space in Claude models. + the global workspace / J-space in Claude models. Full writeup + published: https://jayrup.me/blog/jacobian-lens-frequency - `q1-prediction-to-reasoning/` — Deep dive on Q1: why next-token prediction produces reasoning. Why we can reverse-engineer toy models but not large ones. Sub-questions. diff --git a/anthropic-j-space.md b/anthropic-j-space.md index 7129fec..c494ee3 100644 --- a/anthropic-j-space.md +++ b/anthropic-j-space.md @@ -2,6 +2,7 @@ **Paper:** Gurnee, Sofroniew, Lindsey et al. (Anthropic, July 2026) **URL:** https://transformer-circuits.pub/2026/workspace/index.html +**Full writeup (Jayrup, 2026-08-07):** https://jayrup.me/blog/jacobian-lens-frequency ## Core claim -- cgit v1.2.3