News for hackers. Stuff that matters.

A comment on Why the push for Agentic when models can barely follow a simple instruction?. Parent comment

Re:Why the push for Agentic when models can barely follow a ... by qazxcvbnmlp on Tuesday October 14, 2025 @11:18AM (#45581099)
> My experience has been that if you take the time to explain what the current state is, what your desired state should be, and to give information on how you want the agent to proceed,

I have a pet theory. 1. This skill requires a strong theory of mind[1]. 2. Theory of mind is more difficult in those with autism 3. The same autism that makes people really good at coding, and gives them the time to post on online forms like hn, makes it hard to understand how to work with LLMs and how others work with llms.

To provide good context to the llm you need to have a good understanding of (1) what it will and will not know, (2) what you know and take for granted(ie a theory of your own mind) (3) what your expectations are. None of this you need to do when you are coding on your own, but are critical on getting a good response from the LLM.

See also the black and white thinking that is common in the responses on articles like this.[2]

[1]https://en.wikipedia.org/wiki/Theory_of_mind [2]https://www.simplypsychology.org/black-and-white-thinking-in...

[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by saulpw on Tuesday October 14, 2025 @11:40AM (#45581363)
An LLM has no mind! What is your strong theory of mind for an LLM? That it knows the whole internet and can regurgitate it like a mindless zombie?
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by kelseyfrog on Tuesday October 14, 2025 @03:12PM (#45583626)
Source?

It sounds like an unprovable metaphysical statement than something that is supported by scientific evidence.

[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by fao_ on Tuesday October 14, 2025 @03:47PM (#45583963)
The burden of proof is on people stating that an AI has a theory of mind, not on the reverse. Until recently it was highly debated on if dogs have theory of mind, and it took decades of evidence to come to the conclusion that yes, they do.
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by judahmeek on Tuesday October 14, 2025 @04:47PM (#45584640)
GGP didn't say that AI has a theory of mind. GGP said that using AI productively requires a theory of mind, a.k.a. being able to build a mental model of the LLM's context.
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by kelseyfrog on Tuesday October 14, 2025 @05:26PM (#45585183)
The burden of proof is on the person making the claim. It doesn't matter whether the claim is positive or negative. The default position is "We don't know if AI has a ToM."
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by sirtaj on Wednesday October 15, 2025 @09:28AM (#45592188)
Am I incorrect in thinking this is as much true of the linux kernel or emacs as it is of an LLM?
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by rmwaite on Wednesday October 15, 2025 @12:47PM (#45595283)
If you read carefully you will see that they never said AI has a theory of mind.
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by xg15 on Tuesday October 14, 2025 @07:33PM (#45586252)
Whether or not it has a mind is irrelevant to the problem. I think the point is, if you pretend it had a mind and write your prompt accordingly, you will get the best results.
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by wild_egg on Tuesday October 14, 2025 @04:51PM (#45584686)
This actually makes a disturbing amount of sense and I think I'm going to need to chew on it for a while. Thanks for sharing!
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by bigchillin on Tuesday October 14, 2025 @06:12PM (#45585686)
That simply psych article is a psyop
[ Parent | on HN ]
Re:Why the push for Agentic when models can barely follow a ... by imtringued on Tuesday October 14, 2025 @07:47PM (#45586343)
That HN username is also bad news. Meanwhile yours is pretty cool. I really enjoyed the social credit memes with John Cena.

How exactly do you come up with a pet theory out of nowhere, randomly diagnose people on the internet with autism based on how they use LLMs and then start linking to a most likely AI generated blog post (there was simply too much repetition) that ascribes a lot of negative attributes to them with a username that is meant to be unrecognisable.

The post is basically a Kafka trap or engagement bait.

[ Parent | on HN ]