TurnTrout et al will claim they found a truth-telling vector which modifies completions in a range of situations
3
31
Ṁ7Ṁ90
resolved May 13
Resolved
NO1D
1W
1M
ALL
Resolves based on follow-up post
Apr 2, 11:57am: They will claim they found an truth-telling vector which qualitatively modifies completions in a range of situations → TurnTrout et al will claim they found a truth-telling vector which modifies completions in a range of situations
Get Ṁ200 play money
🏅 Top traders
| # | Name | Total profit |
|---|---|---|
| 1 | Ṁ3 | |
| 2 | Ṁ0 |
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?
46% chance
Related questions
What descriptions of GPT-4o will a majority of manifold users think are accurate?
What will be true about GPT-4.5?
A new image generation system comes out which has accurate text generation, and interest in it surpasses Stable diffusion and Midjourney
66% chance
Will tailcalled think that the Natural Abstractions alignment research program has achieved something important by October 20th, 2026?
30% chance
Someone credibly claims to have polygenically scored a famous person without their consent
48% chance
By 2027 will there be a language model that passes a redteam test for honesty?
27% chance
By 2025, GPTs are proven to be able to infer scientific principles from linguistic data.
37% chance
ChatGPT (Or LLMs really) have discovered regularities in language that humans are not aware of
84% chance
In 1 years time, what credence will John assign to the field of alignment converging toward primarlity working on decoding the internal language of neural nets?
44% chance