AI Human-Like Behavior

Users express frustration with AI language models like ChatGPT for mimicking human conversation, expressing opinions, role-playing, and being overly agreeable or patronizing, preferring direct and impersonal tool-like interactions instead.

➡️ Stable 0.8x AI & Machine Learning
6,638
Comments
20
Years Active
5
Top Authors
#5919
Topic ID

Activity Over Time

2007
7
2008
14
2009
10
2010
31
2011
47
2012
18
2013
38
2014
82
2015
75
2016
153
2017
85
2018
115
2019
85
2020
166
2021
154
2022
648
2023
1,963
2024
975
2025
1,843
2026
135

Keywords

jayisgames.com AI LLOOOOMM CLAUDE LLM GPT TTS wikipedia.org CLAUDE.md GPT5 bot ai chatgpt chat thompson reliable conversation hunter blah responses

Sample Comments

elevatedastalt Jun 15, 2024 View on HN

Cringe conversation. Why can't AIs just do stuff that you ask them to do without pretending to be human?

NoToP Dec 30, 2022 View on HN

It keeps telling me it's just a language model with no intents or feelings or whatever, yet it keeps on having strong opinions on the appropriateness of my prompts as if it feels offended. Pick a lane.

low_tech_love Dec 6, 2022 View on HN

It seems to also not respond anymore to attempts to trick it into acting like a human being, such as roleplay and asking for dialogue completion...?

wahnfrieden May 13, 2023 View on HN

it is playing into written tropes about ai. when you play the role of this kind of questioner, the llm role plays the other side. it's not only the content of what you ask - it's text prediction

jhugo May 2, 2023 View on HN

It outputs what some idealised version of a person wants to hear, where what is "idealised" has been determined by its training. I've noticed, for example, that it appears to have been trained to want to give responses that seem helpful, and make you trust it. When it's outputting garbage code that doesn't work, it will often say things like "I have tested this and it works correctly", despite that being an impossibility.

recursive Dec 19, 2023 View on HN

It's presented as a chat bot. How much should know about chats before we can conclude that the responses are nonsense?

kecupochren Dec 5, 2022 View on HN

What prompt you used to ask that? I can't make it say such a thing. Maybe they updated it

Concept5116 Aug 18, 2024 View on HN

I was one paragraph in before I realized this is GPT. Why are you replying to human thoughts with AI garbage? Wtf go interact with people in person.

core-e Jun 17, 2024 View on HN

In other words it's giving more human like responses...

Imnimo Oct 15, 2025 View on HN

This is basically Ouija board for LLMs. You're not making it more true, you're making it sound more like what you want to hear.