Is the Q-star misterious technique claimed by openAI the same as Quiet-STaR (the paper released by stanford)?
Basic
8
Ṁ418Dec 31
78%
chance
1D
1W
1M
ALL
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Sort by:
https://www.reuters.com/technology/artificial-intelligence/openai-working-new-reasoning-technology-under-code-name-strawberry-2024-07-12/
Strawberry has similarities to a method developed at Stanford in 2022 called "Self-Taught Reasoner” or “STaR”, one of the sources with knowledge of the matter said. STaR enables AI models to “bootstrap” themselves into higher intelligence levels via iteratively creating their own training data, and in theory could be used to get language models to transcend human-level intelligence, one of its creators, Stanford professor Noah Goodman, told Reuters.
Related questions
Related questions
[ACX 2024] Will OpenAI publish information describing Q* (Q-Star) in 2024?
21% chance
Is Q* the A star pathfinding search combined with Q-learning, as claimed in a "tin hat time" tweet?
25% chance
Is OpenAI's Q* real?
90% chance
Did the board of OpenAI recieve a letter about the Q* AI 'breakthrough'?
49% chance
Will Q* (Q Star) be a significant breakthrough in AI/ML research or engineering?
92% chance
Will OpenAI officially mention Q* model before 1.1.2025?
18% chance
Will credible evidence of 4chan's OpenAI Q-star leak be revealed by 2024
3% chance
Did OpenAI make a breakthrough in Q* learning dramatically shortening AGI timelines?
27% chance