For typical SOTA AI systems in 2028, will it be possible for users to know the true reasons for systems making a choice? | Manifold

For typical SOTA AI systems in 2028, will it be possible for users to know the true reasons for systems making a choice?

28

Never closes

Very Unlikely (<10%)

Unlikely (10-40%)

Even odds (40-60%)

Likely (60-90%)

Very likely (>90%)

For typical state-of-the-art AI systems in 2028, do you think it will be possible for users to know the true reasons for systems making a particular choice?

By “true reasons” we mean the AI correctly explains its internal decision-making process in a way humans can understand. By “true reasons” we do not mean the decision itself is correct.

This question is managed and resolved by Manifold.

#️ Technology

#Expert survey on AI progress, 2023

Get

1,000

and

3.00

Sort by:

I would be concerned if we were relying on the AI's explanation of its reasons without being able to verify that explanation. To me, knowing the true reasons implies having interpretability techniques that can reliably decode the meaning of a change in neural net weights. If we are relying on an AI to tell us the reasons for a particular output, then we have built an AI with good self-understanding, but we do not understand that AI very well. Which seems hard to do, and also bad if we manage to do it.

Related questions

Will a SOTA model be trained with Kolmogorov-Arnold Networks by 2029?

Will humans create a SOTA AI model without Multi-Layer Perceptrons by 2029?

When will SOTA for Atari 100k pass human median and mean score on all 57 games?

By 2026, the SOTA in image generation will be using mind reading to control the generation.

BIG-bench accuracy 75% #4: Will SOTA for a single model on BIG-bench pass 75% by the start of 2027?

Will a SOTA open-sourced LLM forecasting system make major use of quasilinguistic neural reps (QNRs) before 2027?

By 2026, the SOTA in image generation will be using a voice chat to control the generation.

Will a Kolmogorov-Arnold Network based model achieve SOTA on some significant machine learning tasks in 2024?

BIG-bench accuracy 75% #5: Will SOTA for a single model on BIG-bench pass 75% by the start of 2028?

Related questions

Will a SOTA model be trained with Kolmogorov-Arnold Networks by 2029?

Will a SOTA open-sourced LLM forecasting system make major use of quasilinguistic neural reps (QNRs) before 2027?

Will humans create a SOTA AI model without Multi-Layer Perceptrons by 2029?

By 2026, the SOTA in image generation will be using a voice chat to control the generation.

When will SOTA for Atari 100k pass human median and mean score on all 57 games?

Will a Kolmogorov-Arnold Network based model achieve SOTA on some significant machine learning tasks in 2024?

By 2026, the SOTA in image generation will be using mind reading to control the generation.

BIG-bench accuracy 75% #5: Will SOTA for a single model on BIG-bench pass 75% by the start of 2028?

BIG-bench accuracy 75% #4: Will SOTA for a single model on BIG-bench pass 75% by the start of 2027?

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules