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

Telling GPT-4 you're scared or under pressure improves performance

aimodels.substack.com

Post reply on HN
Print view View original

41–50 of 255 posts

Re: Telling GPT-4 you're scared or under pressure improves performance

#41

Post by kristiandupont »

visarga wrote: post #18
kristiandupont wrote: post #13

Earlier quoted context omitted.

I had a similar realization recently. I plugged my blog post(1) two days ago and I am doing it again now so I will try and refrain for a while, but it really sticks with me: after trying to create a chat bot for a while, I feel like I have gained significant insights into how humans work. It all seems so simple now! It's a weird and awesome feeling! 1) [link redacted]

> To address this, I implemented a strategy of tagging messages to create and utilize categories. I think before RAG we need to do more legwork with the LLM on the raw text. Here is one of my blog posts that is related: https://mindmachina.wixsite.com/ai-blog/post/the-promise-of-... The idea is to create chain-of-thought annotations from your raw texts, that would improve the embedding and retrieval process by making…

Interesting, thank you!

I think a lot about the cost of the loop, mostly in terms of time. I don't want the bot to take too long to respond. That's why dream cycles seem like an obvious solution to some of the more heavy work. I guess it would make sense to combine those with your idea -- "given what I know about the user, what should I study?", especially if it has access to an "enhanced" knowledge db like you suggest..

Re: Telling GPT-4 you're scared or under pressure improves performance

#42

Post by kristiandupont »

suzzer99 wrote: post #15

Am I the only one who feels bad for asking ChatGPT a "dumb" question that I know I should know, or not saying thank you when it gives me an answer? No? I'm just a weirdo? Okay. I have to push back really hard against my proclivity to humanize it, to the point where I probably don't use it as much as I should, just because I don't want to deal with the psychic stress of reminding myself that it's not a living entity.

I have this too and to be honest, I have made the conscious decision that it is OK. I prefer to retain my habit of being polite even when it's not necessary over getting used to being rude which may then "spill" over to my human-to-human interactions.

Re: Telling GPT-4 you're scared or under pressure improves performance

#43

Post by Matumio »

mo_42 wrote: post #34
intended wrote: post #19

I think this is the entry point needed to get peoples attention and explain: LLMs aren’t people, and emergent properties are being over extended. If LLMs are showing “better” performance when there are tokens that humans read as emotionally salient - Then the underlying text it’s trained on shows humans give better answers when emotionally salient context is provided. LLMs predict words. Any semantic validity is a si…

> LLMs aren’t people, and emergent properties are being over extended. LLMs are trained on human texts. And if they're trained well these models might start to simulate parts of a human brain. Might be that this is the simplest way to produce texts that satisfy the objective function. If this would be the case, and we give LLMs some emotional shading, maybe these would simulate parts of a human brain with this emotio…

It won't ever simulate the human brain. It may simulate human cultural knowledge, or emotions, but only as far as they are encoded in the current millennium's written knowledge.

The human brain doesn't even have the concept of written language, that's all culturally learned knowledge.

Re: Telling GPT-4 you're scared or under pressure improves performance

#44

Post by totetsu »

suzzer99 wrote: post #15

Am I the only one who feels bad for asking ChatGPT a "dumb" question that I know I should know, or not saying thank you when it gives me an answer? No? I'm just a weirdo? Okay. I have to push back really hard against my proclivity to humanize it, to the point where I probably don't use it as much as I should, just because I don't want to deal with the psychic stress of reminding myself that it's not a living entity.

when I worked in customer service lots of small business owners would ramble on to me before getting to what they actually wanted. I think talking is just part of the cognitive processes of putting ones thoughts together.

Re: Telling GPT-4 you're scared or under pressure improves performance

#46

Post by cvs268 »

Matumio wrote: post #43
mo_42 wrote: post #34

Earlier quoted context omitted.

> LLMs aren’t people, and emergent properties are being over extended. LLMs are trained on human texts. And if they're trained well these models might start to simulate parts of a human brain. Might be that this is the simplest way to produce texts that satisfy the objective function. If this would be the case, and we give LLMs some emotional shading, maybe these would simulate parts of a human brain with this emotio…

It won't ever simulate the human brain. It may simulate human cultural knowledge, or emotions, but only as far as they are encoded in the current millennium's written knowledge. The human brain doesn't even have the concept of written language, that's all culturally learned knowledge.

Emulate the brain? No. Simulate the brain? Yes.

Re: Telling GPT-4 you're scared or under pressure improves performance

#47

Post by a_wild_dandan »

intended wrote: post #19

I think this is the entry point needed to get peoples attention and explain: LLMs aren’t people, and emergent properties are being over extended. If LLMs are showing “better” performance when there are tokens that humans read as emotionally salient - Then the underlying text it’s trained on shows humans give better answers when emotionally salient context is provided. LLMs predict words. Any semantic validity is a si…

The “statistical parrot” assertion is pretty thoroughly disproven by this point, but suppose we ignore the literature and just assume it’s true: what does it matter? “Real” people are time bombs too, for instance. Is there some predictive power that we gain by reducing LLM skills to mere token production side effects?

Re: Telling GPT-4 you're scared or under pressure improves performance

#48

Post by alex_duf »

sheikheddy wrote: post #5
jimmytucson wrote: post #2

It’s interesting to think about how generative AI might shape human expression, in the same way Twitter’s algorithm rewards punchy, editorialized content, and Google’s algorithm gave life to all the generic “blogspam-y” content out there. If we increasingly interact with generative AI, would we shape our speech to get more value out of that interaction?

Almost certainly yes.

Presumably the technology would love faster than our speaking habits.

Re: Telling GPT-4 you're scared or under pressure improves performance

#49

Post by Timon3 »

SirMaster wrote: post #14

Am I the only one who doesn't think we should have to do stuff like this to get the best performance? The people who design and control the model should have this type of stuff baked in for us IMO.

This wasn't done deliberately. It's something the model picked up from it's training dataset. I'm sure the creators don't want it to be like this, but cleaning trillions of tokens of all examples is long and hard work.

The alternative would be injecting these sentences into your prompts, which probably nobody really wants to happen.

Re: Telling GPT-4 you're scared or under pressure improves performance

#50

Post by dr_dshiv »

cvs268 wrote: post #46
Matumio wrote: post #43

Earlier quoted context omitted.

It won't ever simulate the human brain. It may simulate human cultural knowledge, or emotions, but only as far as they are encoded in the current millennium's written knowledge. The human brain doesn't even have the concept of written language, that's all culturally learned knowledge.

Emulate the brain? No. Simulate the brain? Yes.

It’s not the brain, it’s the mind or what Plato would have called the Nous.
Post reply on HN