Viewing profile — sandkoan
sandkoan
HN member- Joined
- Sun, Oct 11, 2020, 9:05 PM UTC
- HN karma
- 128
- Public activity
- 99 items
- HN profile
- View on Hacker News ↗
About sandkoan
Recent public activity
-
comment
Comment #43958310
DeepMind.
- story
-
comment
Comment #39997571
See https://musiccontrolnet.github.io/web/
-
comment
Comment #39949312
sudo !!
-
comment
Comment #39438429
Ilya says this here: https://www.youtube.com/watch?v=AKMuA_TVz3A
- story
-
comment
Comment #38181983
For anyone else interested, the paper he's referring to is "The Reversal Curse": https://arxiv.org/abs/2309.12288 .
-
comment
Comment #37908727
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
-
comment
Comment #37489588
This is part of what we're doing at Automorphic. Building shareable, stackable adapters that you can compose like lego bricks.
-
comment
Comment #37128672
This is what we did at Trex ( https://github.com/automorphic-ai/trex ). The tricky part is doing it quickly and efficiently.
-
comment
Comment #36821529
Also using a similar method: https://github.com/automorphic-ai/trex Playground: https://automorphic.ai/playground
-
comment
Comment #36807525
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
Comment #36769426
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 …
-
comment
Comment #36766808
Ahh, no, the value of this isn't as much the model as it is the infrastructure enabling structure enforcement.
- story
-
comment
Comment #36763259
https://news.ycombinator.com/item?id=36752991
-
comment
Comment #36755083
You wouldn't actually want to, because you'd be losing generalizability, and it's a lot of unnecessary work. I think approach #1 outlined above is the better (more cost- and time-e…
-
comment
Comment #36754333
Ahh, I've been meaning to try FLARE—was it a marked improvement over traditional RAG?
-
comment
Comment #36754259
Thanks for the reminder—done!
-
comment
Comment #36753634
This is model agnostic, actually—any model on HuggingFace is compatible. So if someone wanted to run this with their own model, they could.
-
comment
Comment #36753547
Custom LLM—hence the self-hostability.
-
comment
Comment #36753292
Costs add up surprisingly quickly. A quote-colon-space-quote combo alone is four tokens wasted. Now scale that up....
-
comment
Comment #36753284
https://news.ycombinator.com/item?id=36753254 Does this help clarify?
-
comment
Comment #36753254
The prompt is given to our model as a guiding aid (a suggestion), and the cfg is used to constrain the model to generate only tokens that abide by the schema (an enforcement). That…