Development

A training run accidentally ingests a partner's benchmark tasks

development2026-07-09

Claim

The Grok 4.5 run accidentally ingested the Cursor codebase, benchmark tasks included, an asterisk on the results in an era when contamination arrives through corporate structure rather than web scraping.

Reporting date: 2026-07-09 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to July 9, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to July 9, 2026

Actor

Evidence for

Supersedes

A model completes over half of real workflow objectives without breaking rules

Referenced by

Cite or correct this record

Citation formatCitation text

A training run accidentally ingests a partner's benchmark tasks
Innermost Loop KB — secondary record
Reporting date: 2026-07-09
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-07-09-a-training-run-ingests-its-own-benchmark
Claim: The Grok 4.5 run accidentally ingested the Cursor codebase, benchmark tasks included, an asterisk on the results in an era when contamination arrives through corporate structure rather than web scraping.
Attributed sources:
- Welcome to July 9, 2026 — https://theinnermostloop.substack.com/p/welcome-to-july-9-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.