The no-degradation-at-scale claim is the interesting part. Context rot has been the main thing limiting how useful long context actually is in practice — curious to see what independent evals show on retrieval consistency across the full 1M window.

I don't think they're claiming "no degradation at scale", are they? They still report a 91.9->78.3 drop. That's just a better drop than everyone else (is the claim).