Skip to main content

AI capabilities (short- and medium-term) [WIP]

Work in progress. Feedback welcome.

Ṁ550
Will A.I., "Hallucinate Significantly Less," by the End of 2023?
NO
Ṁ550
Ṁ1.5k
Will AIs be widely recognized as having developed a new, innovative, foundational mathematical theory before 2030?
69% chance
Ṁ1.5k
Ṁ1.5k
In 2029, will any AI be able to work as a competent cook in an arbitrary kitchen? (Gary Marcus benchmark #3)
56% chance
Ṁ1.5k
Ṁ1.1k
Will an AI model outperform 95% of Manifold users on accuracy before 2026?
NO
Ṁ1.1k
"Improving AI Benchmarks" by Isabel Juniewicz - Discussion
Ṁ2,500 bounty
Ṁ2.5k
Ṁ1.7k
By 2029, will any AI be able to read a novel and reliably answer questions about it? (Gary Marcus benchmark #2)
89% chance
Ṁ1.7k
Ṁ410
Benchmark Gap #4: Once a single AI model solves >= 95% of miniF2F, MATH, and MMLU STEM, how many months will it be before an AI is listed as a (co) first author on a published math paper?
37
Ṁ410
Ṁ1.3k
By 2029 will any AI be able to watch a movie and accurately tell you what is going on? (Gary Marcus benchmark #1)
87% chance
Ṁ1.3k
Ṁ1k
Benchmark Gap #1: Once we have a language model that achieves expert human performance on all *current* major NLP benchmarks, how many years will it be before we have an AI with human-level language skills?
4.3
Ṁ1k
Ṁ1k
Will a robot capable of passing both the Coffee Test and a strong, adversarial Turing test be created before 2100?
95% chance
Ṁ1k
Ṁ1.2k
In 2029, will any AI be able to take an arbitrary proof in the mathematical literature and translate it into a form suitable for symbolic verification? (Gary Marcus benchmark #5)
77% chance
Ṁ1.2k
Ṁ190
Benchmark Gap #5: Once a single AI model solves >= 95% of miniF2F, MATH, and MMLU STEM, will it be less than two years before AI models are used as entry-level data science / data analysis / statistics workers?
67% chance
Ṁ190
Ṁ490
Will any author of "Clever Hans or Neural Theory of Mind?" say that LLMs have some robust Theory-of-Mind (ToM) in 2026?
44% chance
Ṁ490
Ṁ1k
When will self-improving AI outperform human-developed AI?
2030
Ṁ1k
Ṁ250
Will an AI song have >100m plays? (2023)
NO
Ṁ250
Ṁ1k
Will any Twitter account with at least 10,000 followers be discovered to be an AI during 2023?
NO
Ṁ1k
Ṁ130
will research with at least 50% AI generated content win the Nobel Prize by 2030?
22% chance
Ṁ130
Ṁ4k
Will an AI system be known to have resisted shutdown before 2024?
NO
Ṁ4k
Ṁ330
Will a mostly AI channel reach the top 100 ranking on twitchtracker.com in 2023?
NO
Ṁ330
Ṁ980
Will an AI-authored short story be published in a major science fiction magazine by 2024?
NO
Ṁ980
Ṁ4k
Will an AI system be known to have resisted shutdown before 2024?
NO
Ṁ4k
Ṁ980
Will an AI-authored short story be published in a major science fiction magazine by 2024?
NO
Ṁ980
Ṁ1.5k
Will AIs be widely recognized as having developed a new, innovative, foundational mathematical theory before 2030?
69% chance
Ṁ1.5k
Google
Search the world's information, including webpages, images, videos and more. Google has many special features to help you find exactly what you're looking for.
See more questions: