Will it be possible to disentangle most of the features learned by a model comparable to GPT-2 this decade?
18
1kṀ12752031
89%
chance
1H
6H
1D
1W
1M
ALL
close date: end of 2030
Esta pergunta é gerenciada e resolvida pela Predita.
Get 
1,000 to start trading!
1,000Pessoas também estão operando
Perguntas relacionadas
Will it be possible to disentangle most of the features learned by a model comparable to GPT-4 this decade?
37% chance
Will it be possible to disentangle most of the features learned by a model comparable to GPT-3 this decade? (1k subsidy)
58% chance
Will we fully interpret a GPT-2 level language model by 2028?
12% chance
Will mechanistic interpretability be essentially solved for GPT-2 before 2030?
31% chance
Will OpenAI release a model called GPT-5o in 2026?
11% chance
Will a GPT-3 quality model be trained for under $1,000 by 2030?
90% chance
Will mechanistic interpretability be essentially solved for GPT-4 before 2030?
12% chance
Will mechanistic interpretability be essentially solved for GPT-3 before 2030?
13% chance
Before 2028, will anyone train a GPT-4-level model in a minute?
29% chance
Will a GPT-3 quality model be trained for under $10.000 by 2030?
99% chance