diff options
| author | CaptainJack2491 <jayrupnakawala@gmail.com> | 2026-07-23 15:51:59 +0100 |
|---|---|---|
| committer | CaptainJack2491 <jayrupnakawala@gmail.com> | 2026-07-23 15:51:59 +0100 |
| commit | 93123f06c07459e6d692d7b37f0f880272a4cd7f (patch) | |
| tree | 6c84618dc2fe993e84a889df8898702c00823acf /README.md | |
| parent | ff30674b03ad2f1c163e9940807484d1f4959336 (diff) | |
Add Q1 deep dive: why prediction→reasoning, why scale matters, sub-questions
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 6 |
1 files changed, 4 insertions, 2 deletions
@@ -9,8 +9,10 @@ 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. Directly relevant - to the oversight-vector project. + the global workspace / J-space in Claude models. +- `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. ## Related projects |