10-15-2026, 02:16 AM
Maybe, but I had the opposite result. I've seen people blame tool calling when the real issue was much more mundane.
|
human evals on small teams
|
|
10-15-2026, 02:16 AM
Maybe, but I had the opposite result. I've seen people blame tool calling when the real issue was much more mundane.
10-18-2026, 02:55 AM
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
learning in public
|
|
« Next Oldest | Next Newest »
|