Will Alexplainable recognize one randomly selected class with up to 70% accuracy, autonomously?
0
13
Ṁ100
Jun 6
50%
chance
1D
1W
1M
ALL
Get Ṁ200 play money
AI Alignment questions
By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
49% chance
In the next 6 months, will it be publicly confirmed that Ilya Sutskever and Jan Leike are working on a project together?
50% chance
Related questions
In 2028, will an AI be able to play randomly-selected computer games at human level, given the chance to train via self-play?
64% chance
Will DALL-E 4 be able to generate an image with 10 English words without making any mistakes, at least 50% of the time?
53% chance
Will Alexplainable recognize one randomly selected class with at least 70% accuracy, with human guidance?
63% chance
In 2030, will there be an AI that can write blog posts as good as a 75th percentile ACX post, according to Scott Alexander's judgement?
47% chance
Will an AI model outperform 95% of Manifold users on accuracy before 2026?
67% chance
Will an autonomous agent resolve 90% of tasks on SWE-bench by 2026?
57% chance
Will it be possible to disentangle most of the features learned by a model comparable to GPT-3 this decade? (1k subsidy)
55% chance
Will it be possible to disentangle most of the features learned by a model comparable to GPT-4 this decade?
39% chance