Convergence 3: The Sequential Edge: sequential > parallel in 95.6% of configurations

2 min read · 387 words
Share:
Michael Darius Eastwood
Michael Darius Eastwood · Independent AI alignment researcher
Published
Michael Darius Eastwood · Research Notes · 3 July 2026 · Part of the Research evidence spine
Michael Darius Eastwood, independent researcher, London: originator of the embedded-correction alignment thesis (manuscript 8 December 2024, SHA-256 anchored: f0d1f38f).
Register entry 3 of 19. Domain: AI Reasoning. Institution: Sharma & Chopra. External date: 2025-11-04. Measured against: A1 (directional thesis) (CONCURRENT - they precede MDE's Jan 2026 formalisation by ~2.5mo). Classification: CONCURRENT.
Primary source: arXiv:2511.02309

What happened

The Sequential Edge: sequential > parallel in 95.6% of configurations.

Why it is in the register

This row is in the register to demonstrate that the register is honest. Sharma and Chopra published their quantified sequential-versus-parallel result in November 2025, roughly two and a half months before the programme's own formalisation. Priority on the quantified finding belongs to them, is credited to them and appears in this register under a class that says so. The December 2024 manuscript carried the directional thesis only. A register that only listed favourable rows would be marketing. This row is the audit trail proving it is not.

The honest caveat

Their paper is arXiv:2511.02309. The programme's validation contract for this claim records the deference explicitly.

How to check this entry

Open the primary source above. Confirm the date. Confirm the finding. Then compare it against the manuscript passage or artifact named in the register entry, whose SHA-256 hash is published on the evidence page. Nothing in this article asks for trust; the entry either survives that comparison or it comes off the register, publicly, the way the programme's retracted scaling figure did.

From the book Infinite Architects: Intelligence, Recursion, and the Creation of Everything by Michael Darius Eastwood.

Buy on Amazon UK Amazon US

Stay informed

New posts on AI alignment, convergence evidence, and the ARC/Eden research programme.

Get updates →