site banner

Small-Scale Question Sunday for September 7, 2025

Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?

This is your opportunity to ask questions. No question too simple or too silly.

Culture war topics are accepted, and proposals for a better intro post are appreciated.

1
Jump in the discussion.

No email address required.

Has anyone else experienced the paradox of choice with LLMs? There was a tine when ChatGPT would suggest several follow-up topics after answering my question. I would usually pick none of them. Now it offers just one suggestion, and on softer topics I just say "please go on" 80% of the time. The suggestions are still not this useful when I'm asking a technical question, though.

I find this general problem to be one of the more interesting (though not necessarily strong) flags that LLMs will struggle to be truly ‘agentic’. As much as AI agents are the rage right now, the ones I’ve seen in the wild at work follow very narrow and defined business rules or require significant human intervention.

I don’t know and haven’t thought enough about why this might be but for all of an LLMs contextual intelligence, I see it falling down on making follow up decisions or inferences based on recent past.