Comment by theLiminator 20 hours ago I wish someone ran some sort of representative benchmark suite every X days to see if this occurs. 3 comments theLiminator Reply micycle1 20 hours ago https://marginlab.ai/trackers/codex/ CamperBob2 20 hours ago Unfortunately that seems to be monitoring Sol, not Astra, unless I'm missing something. embedding-shape 20 hours ago I'm not sure how you could run such a benchmark without leaving it possible for the labs to easily detect and fudge the results.
micycle1 20 hours ago https://marginlab.ai/trackers/codex/ CamperBob2 20 hours ago Unfortunately that seems to be monitoring Sol, not Astra, unless I'm missing something.
CamperBob2 20 hours ago Unfortunately that seems to be monitoring Sol, not Astra, unless I'm missing something.
embedding-shape 20 hours ago I'm not sure how you could run such a benchmark without leaving it possible for the labs to easily detect and fudge the results.
https://marginlab.ai/trackers/codex/
Unfortunately that seems to be monitoring Sol, not Astra, unless I'm missing something.
I'm not sure how you could run such a benchmark without leaving it possible for the labs to easily detect and fudge the results.