Dr GPT is smarter when you are polite and spell better in the prompt. I believe u can find some benchmarks proving it.
FLX@lemmy.world 10 months ago
So, not a single developer thought about filtering useless words locally before triggering the request ?
How can they be so dumb ?
muntedcrocodile@lemm.ee 10 months ago
FLX@lemmy.world 10 months ago
They talk about separate messages though, if you just send “thanks” it changes nothing to the answer
Eyekaytee@aussie.zone 10 months ago
How would you filter it?
FLX@lemmy.world 10 months ago
if msg == “thanks” return
Eyekaytee@aussie.zone 10 months ago
thanks, you’re clearly a genius, these LLM providers should pay you a lot of money to implement this, you’d save them millions 🙄
srecko@lemm.ee 10 months ago
That’s pretty much how they cenzor stuff right now.
muntedcrocodile@lemm.ee 10 months ago
U use a smaller cheaper LLM that will inject a 20% hallucination.
Nighed@feddit.uk 10 months ago
The company I worked for tried that as an experiment on how much money it saves.
Absolutely awful, even removing connectives causes problems.
Endmaker@ani.social 10 months ago
The article doesn’t consider these words useless though. They are suggesting that these words may improve response quality.
chaosCruiser@futurology.today 10 months ago
I would argue that being polite also does good to the person writing that line.
spankmonkey@lemmy.world 10 months ago
The author and the writer they quoted are fucking morons.
Dran_Arcana@lemmy.world 10 months ago
Anecdotally, I use it a lot and I feel like my responses are better when I’m polite. I have a couple of theories as to why.
More tokens in the context window of your question, and a clear separator between ideas in a conversation make it easier for the inference tokenizer to recognize disparate ideas.
Higher quality datasets contain american boomer/millennial notions of “politeness” and when responses are structured in kind, they’re more likely to contain tokens from those higher quality datasets.
I haven’t mathematically proven any of this within the llama.cpp tokenizer, but I strongly suspect that I could at least prove a correlation between polite token input and dataset representation output tokens
spankmonkey@lemmy.world 10 months ago
It FEEEEEEEEEEEELS better is what the authors said too. Both articles were completely worthless dreck about how they felt about the responses.
tdawg@lemmy.world 10 months ago
Honestly they were better until recently. GPT (at least) has gotten really good at de-escalation and providing (mostly) factual responses when you get irate
halcyoncmdr@lemmy.world 10 months ago
Please may be useless. Thank you isn’t useless. That tells you that the prior response gave them the answer they were looking for. No response at all could mean that, or that they gave up, or any number of other things.
FLX@lemmy.world 10 months ago
What if it’s a sarcastic thanks ?
Also, the public models are fixed right ? Not perpetually training AFAIK ? So it should really change nothing unless it’s linked to those “thumb up/down” buttons
spankmonkey@lemmy.world 10 months ago
Both authors state that the phrasing from the AI is what is improved, not the accuracy.
CompostMaterial@lemmy.world 10 months ago
And your qualifications in computer science are…?
killeronthecorner@lemmy.world 10 months ago
Hi, I have a degree in computer science and work with AI every day.
Feelings aren’t a good way to measure things scientifically, they are right about that.
But saying that words can just be filtered is easier said than done. You’re back at needing to do a lot of processing to identify and purge these words. This is still going to cost a lot of money and potentially lead to less meaningful inputs. Now you also have to maintain the software that does the word identification, keep it well tested, maintain monitoring and analytics for it, and so on.
So, in short, everyone here is wrong and I’m considering packing it all in and buying a small potato farm with no internet connection.
spankmonkey@lemmy.world 10 months ago
I’m smart enough to know that an article peppered with this is and zero facts is dogshit.
Doesn’t matter how educated someone is when they write a bunch of words about possibilities with no actual evidence. They are morons because they are spouting a bunch of useless speculation about a shitty and unreliable technology and naval gazing about whether ‘being polite’ to a bullshit generator is beneficial. I feel dumber for having read both the article and the linked article.
Viri4thus@feddit.org 10 months ago
You’re being downvoted, this is a perfect example of:
*they hated Jesus because he spoke the truth 😂🤣