ChatGPT is NOT a LLM – GPT is • Hacker News Board

Re: ChatGPT is NOT a LLM – GPT is

#21

Post by vincirufus » Sun, Sep 07, 2025, 3:56 PM UTC

jemiluv8 wrote: post #16

And there goes the enshitification of all that was good about blog posts: human element.

Well there was is a lot of human element and infact this post was an output of conversations with different people talking about LLM and ChatGPT. I guess Claude over did the 'fix grammar and improve the language' instructions.

Re: ChatGPT is NOT a LLM – GPT is

#22

Post by elaus » Sun, Sep 07, 2025, 4:18 PM UTC

This is becoming a problem for me: I like to use LibreChat to interface LLMs (Gemini, GPT-x), because it allows me to pay by usage (instead of 20+ USD per month) and keep a (tiny bit) more of the data under my control.

But the offerings of ChatGPT or Google's AI Studio surpass the feature set of LibreChat by a lot. It used to be just a "better" system prompt, but now it's a lot more.

Re: ChatGPT is NOT a LLM – GPT is

#23

Post by vincirufus » Sun, Sep 07, 2025, 4:28 PM UTC

elaus wrote: post #22

This is becoming a problem for me: I like to use LibreChat to interface LLMs (Gemini, GPT-x), because it allows me to pay by usage (instead of 20+ USD per month) and keep a (tiny bit) more of the data under my control. But the offerings of ChatGPT or Google's AI Studio surpass the feature set of LibreChat by a lot. It used to be just a "better" system prompt, but now it's a lot more.

Yup exactly!! its a subtle change happening under the hood, When people have a good interaction with ChatGPT they attribute it to the LLM, but in most cases, its the agentic features in ChatGPT that wows you and not necessarily the smartness of the large language model.

Re: ChatGPT is NOT a LLM – GPT is

#24

Post by satisfice » Mon, Sep 08, 2025, 1:04 AM UTC

Call it GenAI.

It’s not acting as an agent unless it does something in the world on your behalf.

Re: ChatGPT is NOT a LLM – GPT is

#25

Post by jemiluv8 » Mon, Sep 08, 2025, 5:21 PM UTC

vincirufus wrote: post #21

jemiluv8 wrote: post #16

And there goes the enshitification of all that was good about blog posts: human element.

Well there was is a lot of human element and infact this post was an output of conversations with different people talking about LLM and ChatGPT. I guess Claude over did the 'fix grammar and improve the language' instructions.

My bad. It just had too much of the llm vibe about it.