sandkoan

Joined 6 years ago

Karma

128

Submissions

99

Member since

Oct 11

https://govindgnana.com , https://blog.govindgnana.com

View on Hacker News

Recent submissions

Comment · 1 year ago

Comment · 2 years ago

See https://musiccontrolnet.github.io/web/

Comment · 2 years ago

Comment · 2 years ago

Ilya says this here: https://www.youtube.com/watch?v=AKMuA_TVz3A

New Funding from Andreessen Horowitz quorablog.quora.com

5 sandkoan 2 years ago 1 comments

Comment · 3 years ago

For anyone else interested, the paper he's referring to is "The Reversal Curse": https://arxiv.org/abs/2309.12288.

Comment · 3 years ago

For anyone who's curious, the paper in question, entitled, "Lost in the Middle: How Language Models Use Long Contexts" (https://arxiv.org/abs/2307.03172)

Comment · 3 years ago

This is part of what we're doing at Automorphic. Building shareable, stackable adapters that you can compose like lego bricks.

Comment · 3 years ago

This is what we did at Trex (https://github.com/automorphic-ai/trex). The tricky part is doing it quickly and efficiently.

Comment · 3 years ago

Also using a similar method: https://github.com/automorphic-ai/trex

Playground: https://automorphic.ai/playground

Comment · 3 years ago

Relevant: Built this which generalizes to arbitrary regex patterns / context free grammars with 100% adherence and is model-agnostic — https://news.ycombinator.com/item?id=36750083

Comment · 3 years ago

Yeah, then it seems we agree. I was just pointing out that it's not necessary to finetune OSS models to behave like OpenAI functions if you're able to do something similar to what we did (no tuning involved!).

Comment · 3 years ago

Ahh, no, the value of this isn't as much the model as it is the infrastructure enabling structure enforcement.