Viewing profile — thesephist
thesephist
HN member- Joined
- Thu, Apr 27, 2017, 2:29 PM UTC
- HN karma
- 4,660
- Public activity
- 268 items
- HN profile
- View on Hacker News ↗
About thesephist
computers should work in service of human creativity and curiosity, not the other way around.
www: thesephist.com twitter: @thesephist
Recent public activity
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
-
comment
Comment #40910261
Reminds me a lot of Infinite Craft ( https://neal.fun/infinite-craft/ ). The generative part of language models can make for really fun "single-player" games where you're really co…
- story
- story
- story
- story
- story
- story
- story
- story
- story
-
comment
Comment #37878362
Thanks for sharing Simon! I will note that by training an adapter layer between this autoencoder's embedding space and OpenAI's, it's possible to recover a significant amount of de…
-
comment
Comment #37401398
Definitely possible if supported by transformers.js. If I see enough folks wanting it I'll likely add it at some point.
-
comment
Comment #37401390
This is definitely an interesting idea I've also pondered before. In my experience (just speaking from intuition) what's "easy" for LMs to predict often doesn't line up with our hu…