Hacker News new | ask | show | jobs
by lelanthran 70 days ago
> I totally get the idea but I think next gen models with 10M context and/or 1000tps will make this obsolete.

We've already got 1m context, 800k context, and they still start "forgetting" things around the 200k - 300k mark.

What use is 10M context if degradation starts at 200k - 300k?