Will someone create a LLM/chatbot fine-tuned to Eliezer's LessWrong sequences by EOY2025?
Basic
2
Ṁ402026
66%
chance
1D
1W
1M
ALL
This question is managed and resolved by Manifold.
Get
1,000and
3.00
1,0003.00Sort by:
Apparently there's LessWrong-Amplify-Instruct, an amplified dataset for instruction tuning based on LW posts. It would seem a lot of other models have been fine-tuned using that dataset, particularly Nous's Capybara family of models.
That said, I haven't found any LLMs purpose-finetuned just for LW/rat content
Related questions
Related questions
Who will have the best LLM at the end of 2024 (as decided by ChatBot Arena)?
Will any LLM outrank GPT-4 by 150 Elo in LMSYS chatbot arena before 2025?
13% chance
Who will have the best LLM at the end of 2024 (as decided by ChatBot Arena Ranks)?
Will a lawless LLM chatbot get 10 million daily active users by the end of 2024?
9% chance
Who will have the best LLM at the end of 2025 (as decided by ChatBot Arena)?
Will OpenAI release an LLM moderation tool in 2024?
76% chance
Will I think that the top Chatbot Arena scores accurately reflect which LLMs are most capable and useful at EOY 2024?
41% chance
By the end of 2024, will any LessWrong, EA, or Alignment forum post with at least 100 upvotes be revealed to have been written by an AI?
40% chance
Will OpenAI Release a Chatbot Using the Q* Algorithm in 2024
25% chance
Will there be an LLM which can do fluent conlang translations by EOY 2024?
72% chance