Will LLM hallucinations be down to human-expert rate within months? | Manifold

Will LLM hallucinations be down to human-expert rate within months?

Basic

34

Ṁ7311

resolved Feb 2

Resolved

NO

1D

1W

1M

ALL

Reid Hoffman said:

And there’s a whole bunch of very good R&D on how to massively reduce hallucinations [AI-generated inaccuracies] and get more factuality. Microsoft has been working on that pretty assiduously from last summer, as has Google. It is a solvable problem. I would bet you any sum of money you can get the hallucinations right down into the line of human-expert rate within months. So I’m not really that worried about that problem overall.

Market resolves on 1/31/2024 (bit over 3 months from now) to the result of a publicized bet made by Reid Hoffman, or my discretion if no such bet is made.

This question is managed and resolved by Manifold.

Get

1,000

and

3.00

Sort by:

What will be used as the bar for 'human expert rate'?

Arb for all of 2024:

@Joshua and for longer timelines

Related questions

Will LLM hallucinations be a fixed problem by the end of 2025?

LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?

Will hallucinations (made up facts) created by LLMs go below 1% on specific corpora before 2025?

A year from now, will Manifold think this prediction about the future of LLM's has held up?

At the beginning of 2028, will LLMs still make egregious common-sensical errors?

Will LLM hallucinations be a fixed problem by the end of 2028?

Will LLM hallucinations be "largely eliminated" by 2025?

How Will the LLM Hallucination Problem Be Solved?

Will scaling current methods be enough to eliminate LLM hallucination?

Will an LLM be able to match the ground truth >85% of the time when performing PII detection by 2024 end?

Related questions

Will LLM hallucinations be a fixed problem by the end of 2025?

Will LLM hallucinations be a fixed problem by the end of 2028?

LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?

Will LLM hallucinations be "largely eliminated" by 2025?

Will hallucinations (made up facts) created by LLMs go below 1% on specific corpora before 2025?

How Will the LLM Hallucination Problem Be Solved?

A year from now, will Manifold think this prediction about the future of LLM's has held up?

Will scaling current methods be enough to eliminate LLM hallucination?

At the beginning of 2028, will LLMs still make egregious common-sensical errors?

Will an LLM be able to match the ground truth >85% of the time when performing PII detection by 2024 end?

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