Staff Engineer @ Google + Recommendation Systems Professor @ Columbia University
New York, USA
Joined November 2017
- Tweets406
- Following98
- Followers763
- Likes75
I needed a document from Paris, it drafted a letter in French using other documents it found on my computer and brought me to payment page that prints and mails it.
What happens if you have hundreds of tools? Is the right approach to RL every model after every checkpoint for every new tool?
Doesn鈥檛 that assume there isn鈥檛 another way to make the product without COG that are being tariffed?
Ya I meant why don鈥檛 we do all the logic the docker/proxy is doing behind the API so migration is simple. This feels complicated enough to just use a different model
Why force creating the proxy? Can鈥檛 we just have a custom URL and pass the url and key into the client in Python directly. Simplify the code example
I mostly buy it based on the expected discounted sum of future cash flows. It feels fairly priced right now
This holds true for Cos(emb(t2), emb(t1+t2)) < cos(emb(t2), emb(t2+t1)) as well. So the second string doesn鈥檛 matter.
OpenAIs new embedding seems to really prefer earlier text. Cos(emb(t1), emb(t1+t2)) > Cos(emb(t1), emb(t2+t1)) ~97% of the time of the 1000 examples I tried. Interesting retrieval consideration
