Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
Post image 6
Post image 7
1 / 7
0

Talkie is an AI language model trained only on pre-1931 texts

Boing Boing·Rob Beschizza·5 months ago
#BI72fNst
#store#ms#ai#history#llms#rest
Reading 0:00
15s threshold

"Talkie, let us discuss cricket, not eugenics" Rogistok/Shutterstock There are various LLMs that focus on public domain texts, for ethical or experimental reasons, but most also incorporate modern material (such as Wikipedia) so they have a fully contemporary awareness of history, society, current events and the rest of it. Talkie , however, is a 13B-parameter language model exclusively trained on English texts prior to 1931 . talkie-1930-13b-it was finetuned using a novel dataset of instruction-response pairs extracted from pre-1931 reference works, including etiquette manuals, encyclopedias, and letter-writing manuals. The model then underwent reinforcement learning (online DPO with an LLM-as-a-judge) to improve instruction-following ability. The result is like talking to an educated gentleman of the high imperial era. He is fascinating, amazingly well-read for the time, and yet full of bad ideas. What ideas? Oh, you know the ones.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More