"Improving AI Benchmarks" by Isabel Juniewicz - Discussion
Ṁ2,500 / 2500
bounty left
At Manifest 2023, Isabel Juniewicz spoke about "Improving AI Benchmarks":
Share your comments, reactions, takeaways, or other thoughts below! We'll be awarding mana to our favorite responses; by default, a 500 mana bounty to our 5 favorite entries, as judged by what the speaker, the community, and our conference team likes.
You can see all Manifest 2023 talks here: https://manifold.markets/browse?topic=-manifest-2023-talks
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000People are also trading
Related questions
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
56% chance
In what year will AI achieve a score of 85% or higher on the SimpleBench benchmark?
3/17/32
In what year will AI achieve a score of 95% or higher on the SWE-bench Verified benchmark?
10/7/28
[Carlini questions] Most improvements in best AI systems direct result of the prior generation of AI systems
In what year will AI achieve a score of 95% or higher on the PhysBench benchmark?
2033
Will "A breakdown of AI capability levels focused o..." make the top fifty posts in LessWrong's 2024 Annual Review?
14% chance
Will the ARC Prize Foundation succeed at making a new benchmark that is easy for humans but still hard for the best AIs?
88% chance
Will "What are the best arguments for/against AIs b..." make the top fifty posts in LessWrong's 2024 Annual Review?
14% chance
Will an AI system beat humans in the GAIA benchmark before the end of 2025?
68% chance
Will AiresAI achieve the SoTA model on benchmarks by the end of the year?
13% chance