If algebraic value edits work well in language models, they are also composable
6
26
Ṁ71Ṁ150
resolved May 13
Resolved
YES1D
1W
1M
ALL
Resolves according to follow-up post.
Get Ṁ200 play money
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ17 | |
2 | Ṁ6 | |
3 | Ṁ5 | |
4 | Ṁ3 |
AI Alignment questions
By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
49% chance
In the next 6 months, will it be publicly confirmed that Ilya Sutskever and Jan Leike are working on a project together?
44% chance
Related questions
Will any language model trained without large number arithmetic be able to generalize to large number arithmetic by 2026?
69% chance
What will be the most common word we use for processing text with large language models?
Eliezer Yudkowsky is impressed by a machine learning model, and believes that the model may be very helpful for alignment research, by the end of 2026
29% chance
Will the first AGI be a large language model?
25% chance
are LLMs easy to align because unsupervised learning imbues them with an ontology where human values are easy to express
32% chance
Will language models be able to solve simple graphical mazes by the end of 2025?
65% chance
By 2025, GPTs are proven to be able to infer scientific principles from linguistic data.
37% chance
Geometric Deep Learning
Ṁ366