esha_manideep
Joined 3 years ago
Karma
35
Submissions
8
Member since
Apr 7
Recent submissions
Comment · 1 year ago
Latest cursor update where they started charging for tokens is pretty good. I don't use non-MAX mode on cursor anymore
Comment · 1 year ago
Claude's limits are so vague - its not clear if buying Claude Max is cheaper than just using the API. Has anyone benchmarked this?
Comment · 2 years ago
They check after they scrape
Comment · 2 years ago
Great work guys! How did you benchmark traiser's 10-20% better? Would love to see exactly how each method scored
Comment · 2 years ago
Pretty amazing to see training data being discussed more openly
Comment · 2 years ago
These models will are compatible with llama.cpp out of the box, we (GigaML - https://gigaml.com) are planning to train a small model (3-4B, 1-bit, opensource) with the latest stack-v2 dataset released today. Let me know if anyone is interested in collaborating with us.
Comment · 2 years ago
Having a feature to summarise the website would be a much better than the first two. As I constantly find myself wishing for such a feature :/