//
sign in
Profile
by @danabra.mov
Profile
by @dansshadow.bsky.social
Profile
by @jimpick.com
AviHandle
by @danabra.mov
AviHandle
by @dansshadow.bsky.social
AviHandle
by @katherine.computer
EventsList
by @katherine.computer
ProfileHeader
by @dansshadow.bsky.social
ProfileHeader
by @danabra.mov
ProfileMedia
by @danabra.mov
ProfilePlays
by @danabra.mov
ProfilePosts
by @danabra.mov
ProfilePosts
by @dansshadow.bsky.social
ProfileReplies
by @danabra.mov
Record
by @atsui.org
Skircle
by @danabra.mov
StreamPlacePlaylist
by @katherine.computer
+ new component
Profile
Loading...
A latent space odyssey gracekind.net
Grace








Loading...
For fans of Talkie-1930 and all the methodological questions raised by historical models, here's a new entrant into the field, TypewriterLM, trained up to 1913. Corpus, instruction-tuning datasets, and event dataset are released. arxiv.org/abs/2606.02991
23h
We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availabilit...
arxiv.org
Pretraining Language Models on Historical Text
less infra overhead = more product velocity. exactly.
1d
Ted Underwood
This account has 4.9K followers
Claude Silly Stories for Little Babies
Prior dense Claudish example
What 9 hours of load-bearing honesty does to a model
Sorry I’m a little on edge, it’s my first singularity
Blade runner (2026)
Grace
1d
1d
1d
1d
21h