+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Evals (https://www.datasculpting.ai/inference/forumdisplay.php?fid=66)
+--- Thread: human evals on small teams: early impressions (/showthread.php?tid=381)
human evals on small teams: early impressions - signaltrack44 - 09-21-2026
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once small local stacks becomes important.
Trying to avoid rebuilding the whole thing twice.
This is mostly for local work rather than public serving.
Re: human evals on small teams: early impressions - southpatch - 09-21-2026
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?