The speaker says their team used context compaction from the beginning, when context windows were much smaller, citing 50,000, 250,000, and 250 tokens.

“I think YCR has been like one generation ahead of coding agents like we've all in the last two years solved things that felt like so alien but very tangible for us which now when we see coding agents you're like man compaction we we were doing compaction from day one like we knew like after five tons or ten tons when your context was only 250 tokens or 250,000 tokens or 50,000 tokens”