News for hackers. Stuff that matters.

A comment on I don't think AGI is right around the corner. Parent comment

Re:I don't think AGI is right around the corner by root_axis on Sunday July 06, 2025 @06:40PM (#44484769)
At the very least, it needs to be able to collate training data, design, code, train, fine tune and "RLHF" a foundational model from scratch, on its own, and have it show improvements over the current SOTA models before we can even begin to have the conversation about whether we're approaching what could be AGI at some point in the future.
[ Parent | on HN ]
Re:I don't think AGI is right around the corner by kadushka on Sunday July 06, 2025 @08:10PM (#44485361)
I cannot do all that. Am I not generally intelligent?
[ Parent | on HN ]
Re:I don't think AGI is right around the corner by root_axis on Monday July 07, 2025 @05:31PM (#44494874)
You could if you were trained to do so. LLMs cannot, even if they are.
[ Parent | on HN ]
Re:I don't think AGI is right around the corner by kadushka on Monday July 07, 2025 @06:25PM (#44495228)
Are LLMs trained to do all that? How do you know they cannot?
[ Parent | on HN ]
Re:I don't think AGI is right around the corner by root_axis on Tuesday July 08, 2025 @01:59AM (#44497490)
> Are LLMs trained to do all that

Yes, they are trained to do all that more or less as much as anything else they are trained to do.

> How do you know they cannot?

The same way I know they can't run a fortune 500 company. It's clearly apparent.

[ Parent | on HN ]
Re:I don't think AGI is right around the corner by kadushka on Tuesday July 08, 2025 @10:00AM (#44500052)
Last time I checked they were trained to predict the next word. Why would you expect them to solve research problems?
[ Parent | on HN ]
Re:I don't think AGI is right around the corner by root_axis on Wednesday July 09, 2025 @10:39AM (#44510587)
> Why would you expect them to solve research problems?

I don't.

[ Parent | on HN ]
Re:I don't think AGI is right around the corner by kadushka on Thursday July 10, 2025 @12:40PM (#44522873)
Great, then we established that I (generally intelligent human), and LLMs, both can't perform the task in question without specific training. We still don't know if given that specific training we (a specific human or a specific LLM) would be able to perform it.
[ Parent | on HN ]