Vintage Large Language Models
Transcript of a talk on vintage large language models — LLMs trained on data up to a particular past date, for epistemic AI, forecasting, and historical simulation.
This is the transcript of a short talk on vintage large language models. A video of the talk is available here and the slide deck is here. Vintage Large Language Models: Transcript I'm going to talk about vintage large language models. The idea is to introduce language models trained on past data. We are sending language models back into the past - into Roman times, the Tudor era, the 1960s, or more recent decades. What is a Vintage LLM? A vintage LLM is a large language model trained on texts and potentially images or other multimodal data up to a particular date. The date could be…
saved by
related reading
- Introducing talkie: a 13B vintage language model from 1930talkie-lm.com
- Why didn't we get GPT-2 in 2005?dynomight.net
- Introducing talkie: a 13B vintage language model from 1930simonwillison.net
- A History of Large Language Modelsgregorygundersen.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Large Language Model: world models or surface statistics?thegradient.pub
- Taking LLMs Seriously (As Language Models) — LessWronglesswrong.com
- GitHub - DGoettlich/history-llms: Information hub for our project training the largest possible historical LLMs.github.com
- Deep Dive into LLMs like ChatGPTyoutube.com
- Large Language Diffusion Modelsarxiv.org
- What language do language models speak?tcz.hu
- Productizing Large Language Modelsblog.replit.com