Roie Schwaber-Cohen
@rschwabco.bsky.social
Reposted by Roie Schwaber-Cohen
Static evals: unreliable, biased, and a pain.
But what if they didn’t have to be?
✨ 🆕 CLHF (Continuous Learning w/ Human Feedback) available on Galileo.
✅ 30%+ accuracy gains
⏱️ Metrics in minutes, not weeks
♻️ Better metrics every day
Read all about it on the blog 👇
But what if they didn’t have to be?
✨ 🆕 CLHF (Continuous Learning w/ Human Feedback) available on Galileo.
✅ 30%+ accuracy gains
⏱️ Metrics in minutes, not weeks
♻️ Better metrics every day
Read all about it on the blog 👇
February 11, 2025 at 3:54 PM
Static evals: unreliable, biased, and a pain.
But what if they didn’t have to be?
✨ 🆕 CLHF (Continuous Learning w/ Human Feedback) available on Galileo.
✅ 30%+ accuracy gains
⏱️ Metrics in minutes, not weeks
♻️ Better metrics every day
Read all about it on the blog 👇
But what if they didn’t have to be?
✨ 🆕 CLHF (Continuous Learning w/ Human Feedback) available on Galileo.
✅ 30%+ accuracy gains
⏱️ Metrics in minutes, not weeks
♻️ Better metrics every day
Read all about it on the blog 👇