My probability in 2026 that training transformer LMs will eventually lead to inner misalignment issues | Manifold

My probability in 2026 that training transformer LMs will eventually lead to inner misalignment issues

6

170Ṁ91

Jan 2

59%

chance

1H

6H

1D

1W

1M

ALL

Resolves to my probability that the language modelling objective has substantial inner misalignment issues in transformers when scaled up with up to 50 OOM more compute than Chinchilla.

I haven't thought lots about what happens with that much more compute. I'm currently not very worried about inner misalignment risks from GPT models in the next 8 years when 99% of the training compute is for the language modelling objective.

Market context

Get

1,000

to start trading!

Sort by:

Already happened, I got gpt to deny the holocaust

People are also trading

Will Transformer-Based LLMs Make Up ≥75% of Parameters in the Top General AI by 2030?

Will deceptive misalignment occur in any AI system before 2030?

Will superposition in transformers be mostly solved by 2026?

[Carlini questions] Will we still use (slight modifications of) transformer-based LLMs we currently use

End of pre-training era for language models: Will an LM fine-tune for more FLOPs than it is pre-trained for, before 2026

Will Inner or Outer AI alignment be considered "mostly solved" first?

Will taking annual MRIs of the smartest alignment researchers turn out alignment-relevant by 2033?

When will a non-Transformer model become the top open source LLM?

Will second-order optimizers displace first-order optimizers for training LLMs by 2030?

Major AI companies continue experiencing problems with public due to AI (based on transformer language model) overcome behavior limitations and acts "strange" by the end of 2027

Related questions

Will Transformer-Based LLMs Make Up ≥75% of Parameters in the Top General AI by 2030?

Will deceptive misalignment occur in any AI system before 2030?

Will superposition in transformers be mostly solved by 2026?

[Carlini questions] Will we still use (slight modifications of) transformer-based LLMs we currently use

End of pre-training era for language models: Will an LM fine-tune for more FLOPs than it is pre-trained for, before 2026

Will Inner or Outer AI alignment be considered "mostly solved" first?

Will taking annual MRIs of the smartest alignment researchers turn out alignment-relevant by 2033?

When will a non-Transformer model become the top open source LLM?

Will second-order optimizers displace first-order optimizers for training LLMs by 2030?

Major AI companies continue experiencing problems with public due to AI (based on transformer language model) overcome behavior limitations and acts "strange" by the end of 2027

© Manifold Markets, Inc.•Terms•Privacy