From ff30674b03ad2f1c163e9940807484d1f4959336 Mon Sep 17 00:00:00 2001 From: CaptainJack2491 Date: Thu, 23 Jul 2026 15:47:52 +0100 Subject: Initial commit: fundamental questions + Anthropic J-space paper summary --- README.md | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 README.md (limited to 'README.md') diff --git a/README.md b/README.md new file mode 100644 index 0000000..9033f73 --- /dev/null +++ b/README.md @@ -0,0 +1,27 @@ +# Research + +Long-term agenda: understand how AI models actually work internally. +Not benchmark scores, not behavioral phenomenology — the computational +mechanisms. + +## Contents + +- `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. Directly relevant + to the oversight-vector project. + +## Related projects + +- `~/Projects/oversight-vector/` — Measuring behavioral shift vectors + under oversight (may pivot given J-space findings) +- `~/uni/dis/` — Dissertation on oversight cues and LLM deception + +## Status + +Pre-experiment. Identifying the right questions before designing +experiments. The Anthropic J-space paper may fundamentally change +the approach to oversight-vector — the J-lens provides direct access +to internal representations, making surface behavioral measurement +potentially obsolete. -- cgit v1.2.3