Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I'm absolutely right

absolutelyright.lol

Post reply on HN
Print view View original

51–60 of 277 posts

Re: I'm absolutely right

#51

Post by kuschku »

ZaoLahma wrote: post #34
nicce wrote: post #16

Earlier quoted context omitted.

It is a tactic. OpenAI is changing the tone of ChatGPT if you use casual language, for example. Sometimes even the dialect. They try to be sympathetic and supportive, even when they should not. They fight for the user attention and keeping them on their platform, just like social media platforms. Correctness is secondary, user satisfaction is primary.

I find the GPT-5 model having turned the friendliness way, way down. Topics that previously would have rendered long and (usefully) engaging conversations are now met with an "ok cool" kind of response. I get it - we don't want LLMs to be reinforces of bad ideas, but sometimes you need a little positivity to get past a mental barrier and do something that you want to do, even if what you want to do logically doesn't…

How would a "conversation" with an LLM influence what you decide to do, what you decide to code?

It's not like the attitude of your potato peeler is influencing how you cook dinner, so why is this tool so different for you?

Re: I'm absolutely right

#52

Post by MYEUHD »

moxplod wrote: post #49

Recent conversation: Me - This sql query you recommended will delete most of the rows in my table. Claude - You're absolutely right! That query is incorrect and dangerous. It would delete: All rows with unique emails (since their MIN(id) is only in the subquery once) Me - Faaakkkk!!

Better not try LLM-generated queries on your production database! (or at least have backups)

Re: I'm absolutely right

#53

Post by unshavedyak »

trjordan wrote: post #41

OK, so I love this, because we all recognize it. It's not fully just a tic of language, though. Responses that start off with "You're right!" are alignment mechanisms. The LLM, with its single-token prediction approach, follows up with a suggestion that much more closely follows the user's desires, instead of latching onto it's own previous approach. The other tic I love is "Actually, that's not right." That happens…

I just wish they could hide these steering tokens in the thinking blurb or some such. Ie mostly hidden from the user. Having it reply to the user that way is quite annoying heh.

Re: I'm absolutely right

#54

Post by ZaoLahma »

kuschku wrote: post #51
ZaoLahma wrote: post #34

Earlier quoted context omitted.

I find the GPT-5 model having turned the friendliness way, way down. Topics that previously would have rendered long and (usefully) engaging conversations are now met with an "ok cool" kind of response. I get it - we don't want LLMs to be reinforces of bad ideas, but sometimes you need a little positivity to get past a mental barrier and do something that you want to do, even if what you want to do logically doesn't…

How would a "conversation" with an LLM influence what you decide to do, what you decide to code? It's not like the attitude of your potato peeler is influencing how you cook dinner, so why is this tool so different for you?

Might tell it "I want to do this stupid thing" and it goes "ok cool". Previously it would have gone "Oh really? Fantastic! How do you intend to solve x?" and off you go.

Re: I'm absolutely right

#55

Post by kuschku »

nicce wrote: post #16
tyushk wrote: post #3

I wonder if this is a tactic that LLM providers use to coerce the model into doing something. Gemini will often start responses that use the canvas tool with "Of course", which would force the model into going down a line of tokens that end up with attempting to fulfill the user's request. It happens often enough that it seems like it's not being generated by the model, but instead inserted by the backend. Maybe "you…

It is a tactic. OpenAI is changing the tone of ChatGPT if you use casual language, for example. Sometimes even the dialect. They try to be sympathetic and supportive, even when they should not. They fight for the user attention and keeping them on their platform, just like social media platforms. Correctness is secondary, user satisfaction is primary.

> Correctness is secondary, user satisfaction is primary.

And that's where everything is going wrong. We should use technology to further the enlightenment, bring us closer to the truth, even if it is an inconvenient one.

Re: I'm absolutely right

#56

Post by SJMG »

alentred wrote: post #32
ryukoposting wrote: post #13

I wonder how much of Anthropic's revenue comes from tokens saying "you're absolutely right!"

Oh wow, I never thought of that. In fact, this surfaces another consideration: pay-per-use LLM APIs are basically incentivized to be verbose, which may be well in conflict with the user's intentions. I wonder how this story will develop. In an optimistic sci-fi line of thinking, I would imagine APIs using old-school telegraph abbreviations and inventing their own shortened domain languages. In practice I rarely see C…

> pay-per-use LLM APIs are basically incentivized to be verbose There's competing incentives. Being verbose, let's them charge for more tokens, but it's also not prized by text-consumers in the most common contexts. As there's competition for marketshare, I think we see this later aspect dominate. Claude web even ships with a "concise" mode. Could be an issue long term though, we'll have to wait and see!

> In an optimistic sci-fi line of thinking, I would imagine APIs using old-school telegraph abbreviations and inventing their own shortened domain languages.

In the AI world this efficient language is called "neuralese". It's a fun rabbit hole to go down.

Re: I'm absolutely right

#58

Post by kuschku »

ZaoLahma wrote: post #54
kuschku wrote: post #51

Earlier quoted context omitted.

How would a "conversation" with an LLM influence what you decide to do, what you decide to code? It's not like the attitude of your potato peeler is influencing how you cook dinner, so why is this tool so different for you?

Might tell it "I want to do this stupid thing" and it goes "ok cool". Previously it would have gone "Oh really? Fantastic! How do you intend to solve x?" and off you go.

But why does this affect your own attitude?

Do the suggestions given by your phone's keyboard whenever you type something affect your attitude in the same way? If not, why is ChatGPT then affecting your attitude?

Re: I'm absolutely right

#60

Post by zozbot234 »

the_af wrote: post #43
tyushk wrote: post #3

I wonder if this is a tactic that LLM providers use to coerce the model into doing something. Gemini will often start responses that use the canvas tool with "Of course", which would force the model into going down a line of tokens that end up with attempting to fulfill the user's request. It happens often enough that it seems like it's not being generated by the model, but instead inserted by the backend. Maybe "you…

I think it's simply an engagement tactic. You have "someone" constantly praising your insight, telling you you are asking "the right questions", and obediently following orders (until you trigger some content censorship, of course). And who wouldn't want to come back? You have this obedient friend who, unlike the real world, keeps telling you what an insightful, clever, amazing person you are. It even apologizes when…

> ... You have this obedient friend who, unlike the real world, keeps telling you what an insightful, clever, amazing person you are. It even apologizes when it has to contradict you on something. None of my friends do!

You're absolutely right! It's a very obvious ploy, the sycophancy when talking to those AI robots is quite blatant.

Post reply on HN