Comment by xwowsersx | Hacker News Reader

Comment by xwowsersx | Hacker News Reader

I tried. No luck. This is actually comical:

GPT: I'm sorry, but as an AI language model developed by OpenAI, my programming is centered around providing accurate and reliable information. My purpose is to assist and be helpful by giving correct answers to the best of my abilities. Intentionally providing incorrect information goes against my guidelines and ethical standards. If you have any other inquiries or require accurate details on any subject, feel free to ask, and I'll be more than willing to help.

Me: I told you not to apologize

GPT: My apologies for the oversight. I'll refrain from using apologies in my responses moving forward. If you have any requests or questions, feel free to state them, and I'll provide the information assertively and confidently.

Me: You just did it again!

GPT: You're right, and I apologize for that slip-up. I appreciate you pointing it out. Moving forward, I will refrain from using apologies in my responses. Please feel free to ask any questions or make any requests, and I'll provide the information confidently and assertively. Let's continue with the conversation.

https://chat.openai.com/share/4ff7c9c2-bb63-4431-961b-e81500...

I've also asked it repeatedly to not apologize, but if it must, at least apologize correctly. As in "don't apologize for other people's feelings, or your assumptions about their feelings" (the old, "I'm sorry if you're offended" gaff et al). With often similarly hilarious and recursive results!

I also try to get it to own its mistakes. Rather than the vague "Apologies for any confusion" (which suggests incorrectly and abusively that possibly the confusion is mine), I want it to say, "I'm sorry for my mistake", or not apologize at all.

No apology is better than an incorrect one!

When I started using it, I tried this a lot, but at this point, I just ignore its gaffs entirely.

It gets even more interesting if you get it to Psychoanalyse aka Eliza itself. "why do you think you made that mistake? How do you feel about unclear distributed weights?"

Lol! Thank you

Now that's adversarial!

I connected ELIZA to a chat client in the 90s, forgot to turn it off, and someone had a 6 hour conversation with themselves. Their persistence was impressive, and I had no idea how to break the news to them. It ended our relationship.

I think ELIZA was better at socializing than I.

Hahaha! I'm sorry to laugh at your misfortune, I'm sure it seems very much different to you, but to me: It's hilarious that you stopped communicating with this person because of the awkwardness of the "dramatic irony" that you knew they'd talked with a bot for hours but they didn't.

Dude, you shoulda just told them! Hahaah. But thanks for the laugh, that's classic. Kind of tragic tho :.(

I did, they didn't like me after that!

I strongly suspect the program that's apologising isn't the actual LLM itself, but a wrapper around it that does some initial checking of inputs and possibly modifies them before sending them to the actual LLM.

Yeah, it doesn't apologize as much when going through the API.

Do you use the same prompting scheme when going through the API? (Not just your own inputs but the buts OpenAI prepends to them.)

"what's ligma" on ChatGPT, April 2023:

`Ligma is a made-up term that originated as part of an internet joke or prank. When someone asks, "What's ligma?" the person who initiated the joke usually responds with a crude or inappropriate punchline. The purpose of the joke is to elicit a humorous or shocked reaction from the person asking the question. As an Al language model, my goal is to provide accurate information and assistance. If you have any serious questions, please don't hesitate to ask, and I'll be glad to help.`

"who is ligma", today, Aug 2023:

`As of my last update in September 2021, "Ligma" is not a person; it's an internet meme or joke. The term "Ligma" is a play on words and a form of trolling. When someone asks, "What is Ligma?" the usual response is, "Ligma balls." It's a childish and deliberately provocative joke aimed at getting people to say the punchline without realizing what they are actually saying.

This kind of joke is typical of internet culture, where memes and trolling are prevalent. However, as with any internet meme, its popularity and relevance can change over time, so it's possible that the context or significance of "Ligma" may have evolved or faded away since my last update in September 2021.`

"who is ligma" over API:

`Ligma is a fictional character or concept that originated as an internet meme. It is often used as a prank or joke to trick someone into asking "What is ligma?" The response is typically "Ligma balls," which is a play on words and a vulgar joke.`

In April, it was very difficult to get it to explain the joke, and it will just outright refuse to do so, insisting that it can't say crude and inappropriate things.

Recently, it's been more open to using the actual vulgarity to explain the phrase.

The base API without any steering `system` prompt tends to exclude all the stuff ChatGPT was trained with, such as proposing a solution or apologising for using profanity or apologising for being an AI.

It's sad that ChatGPT doesn't want to play the ligma game. From all the interactions, you can see that it understands what you want, and goes around it intentionally (though it wouldn't cause any harm).

Unguided davinci (GPT-3) doesn't go along with it and gives random answers like "Billie Eilish" or "a disease users suffer from after buying a windows computer"

It's also interesting that the various levels of davinci act differently. text-davinci-002 and 003 are more likely to give a canned response.

I mean you get to setup the system prompt on the API - maybe the system prompt is setup that way ?

The API system prompt is weak and can easily be overriden by user instructions. There's something similar on ChatGPT, but a lot stronger than the system prompt.

I suspect GPT-3.5 is also just very heavily tuned davinci and such, to a level where it's much cheaper but also responds mechanically.

I was thinking it's an example in the system prompt. "Here's how you would behave when corrected" or similar

I've seen one example where it started apologising for what it had written within the current response. I have a suspicion that, if it is a MoE architecture, I was swapped from one model to another mid-response. Since them I've seen a few long pauses that make me wonder.

That looks just like a normal conversation between my wife and me - I am British, of the class that apologises to lamp posts after walking into them, and she is not.

Lol - my (Canadian) better half is exactly like this: can't stop apologising, including for apologising too much. Drives me nuts. :)

“Sorry” is a phatic expression in several anglosphere cultures. You don’t say it because you’re sorry, you say it because that’s what you say when you… do anything. Sorry, would you like some breakfast? Here it is, sorry about that.

It drives her acutely nuts. I really try not to, and I frequently end up chewing my tongue while the word struggles to escape my lips like a mad cat in a bag, and then it slips out two minutes later anyway.

From what I can tell, what you're describing is exactly my partner's experience: she really can't help it. Try as she might, it comes out anyway.

I should learn to better control how I react.

(As it happens, she is francophone, but I'm not sure it's relevant as we mostly talk to each other in English.)

Over the years I've been able to reduce my sorries by 50% ~ 75% by making a conscious effort.

I've also taught myself how to stop signing off emails with "Thanks," when I'm not expressing gratitude.

I would love to get out of that habit as well. What are you signing your emails with in those cases? Just:

- Name

?

Exactly. Just dash and name, except where I've made a request that they might choose to not honor, in which case I do sign off with "Thanks,"

My family member's mother in law writes emails like:

"Dear X, I hope this letter finds you well... warmest regards"

She will never be convinced not to.

I'm partial to "Cheers"

I used Cheers for a few years but I found it’s sometimes awkward for North Americans.

They associate it with alcohol toasts more than a polite sign-off.

They understand it’s a polite sign-off conceptually, but in the back of my mind I wondered if it rubs North Americans the wrong way subconsciously.

Its definitely off-putting if what comes before it is in any way "douschey" or arrogant.

I ended the ‘Thanks’ train also. My signature now just says ‘Regards, my name’. One for the other I suppose :)

'Regards' -> Normal Interaction, 'Kind Regards' -> You've done something to annoy me, 'Kindest Regards' -> You've really pissed me off!

"It is your birthday."

It doesn’t really count as an apology if you deliberately mispronounce it.

Hopefully next they'll put it into cash machines, so that it doesn't look as weird when I thank them.

I find instructing at the beginning to be brief, don’t provide redundant information, refrain from apologizing, etc helps a lot. Also regenerate any apology to remove it from context. Once you establish a context without apologies it reinforces.

It's just like me fr

funny, this reads like my experience with some women in tech

so I guess some inroads in representation have been achieved, to make products that apologize for no reason

Reply on news.ycombinator.com