Archive
The whole record on one page: every month with its weeks and catch-ups, then the meetings, the challenges, and the reference pages.
Newest first. For a specific fact, search is faster.
June 2026
The cross-entropy track lands, nakaprop gets its name, the caffeine benchmark forms, and the month's thesis becomes equation solving with multiplicative updates.
May 2026
Yad's wave-build swarms ship the hinton and schmidhuber catalogs, the lab spreads into four challenges, and wikitext opens a language-modeling front.
Weeks: May 4 · May 11 · May 18 · May 25 Catch-ups: May 20
April 2026
ByteDMD becomes the primary metric, Yad and Seth measure how far methods sit from the floor, and Yaroslav pivots to modeling energy directly.
Weeks: Apr 6 · Apr 13 · Apr 20 · Apr 27 Catch-ups: Apr 30
March 2026
SutroYaro is born, Yad's survey settles sparse parity with GF(2), and the metric shifts from ARD to data movement.
Weeks: Mar 2 · Mar 9 · Mar 16 · Mar 23 · Mar 30 Catch-ups: Mar 22
February 2026
The group forms around one thesis, that AI training sits far above its energy floor, and starts hunting for a toy problem fast enough to iterate on.
Weeks: Feb 9 · Feb 16 · Feb 23
Meeting notes
- Meeting 1: Energy Intro
- Meeting 2: Forward-Forward Algorithm
- Meeting 6: Emmett Results
- Meeting 6 Notes
- Meeting 7 Notes
- Meeting 8 AI Notes
- Meeting 8 Notes
- Meeting 9 Agenda
- Meeting 9 Notes
Challenges
- Challenge #3: Sparse parity on the grid
- Challenge #2: Energy-efficient matmul
- Challenge #1: Sparse parity
- Challenge #4: wikitext