Doug Colkitt: community effort reaches κ = 2^-15 on OpenAI problem #109
Doug Colkitt @0xdougX
Why it matters
Marks the shift to a crowdsourced effort: Colkitt merges Rohan Arun’s PR and calls the result ‘a true community effort’.
Summary
Posted 15:30 UTC on 8 Oct. Quotes Rohan Arun’s post on PR #40 (‘Mostly used Codex here but Claude collaborating on the other side might have helped’). The repository’s release notes record the reviewed PR #39 witness κ ≈ 3.887×10^-5 > 2^-15.
Archived text
Validated and merged Rohan’s PR. Big gain on a really difficult regime (that frankly I was stuck at). Incredible work.
κ = 2⁻¹⁵ (tightened from κ = 2⁻¹⁸²)
A 500 thousand fold improvement over the previous result and a 2 ^ 167 fold improvement over the original OpenAI result.
This result was a true community effort that combined techniques from a number of contributors. I want to take time to highlight each of them, but for now getting these results verified and published as fast as possible so everyone working on the problem is at the leading edge.
Quoting @RohanArun: So cool! The improvements in the end started getting faster than we could run the verifications.