"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
[Carlini questions] Most improvements in best AI systems direct result of the prior generation of AI systems
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
Will "The case for ensuring that powerful AIs are c..." make the top fifty posts in LessWrong's 2024 Annual Review?
88% chance
Will "The Checklist: What Succeeding at AI Safety W..." make the top fifty posts in LessWrong's 2024 Annual Review?
36% chance
Will AI top level capabilities generally be judged by question and answer benchmarks in 2029?
25% chance
Markers for conscious AI #1: AI passes introspection on world-models test