Hi! I wanted to share a website I made that tracks how quickly AI systems catch up to human-level performance on benchmarks. I noticed this 'catch-up time' has been shrinking dramatically - from taking 6+ years with ImageNet to just months with recent benchmarks. The site includes an interactive timeline of 14 major benchmarks with their release and solve dates, plus links to papers and source data.
I did not see anything about how the estimated time to human level performance of an AI was estimated and what the error bounds might be on those estimates?
Hi! I wanted to share a website I made that tracks how quickly AI systems catch up to human-level performance on benchmarks. I noticed this 'catch-up time' has been shrinking dramatically - from taking 6+ years with ImageNet to just months with recent benchmarks. The site includes an interactive timeline of 14 major benchmarks with their release and solve dates, plus links to papers and source data.