Register | Sign In


Understanding through Discussion


EvC Forum active members: 52 (9179 total)
2 online now:
Newest Member: Jorge Parker
Post Volume: Total: 918,168 Year: 5,425/9,624 Month: 450/323 Week: 90/204 Day: 6/26 Hour: 1/2


Thread  Details

Email This Thread
Newer Topic | Older Topic
  
Author Topic:   Please Welcome ChatGPT
Rahvin
Member
Posts: 4046
Joined: 07-01-2005


(1)
Message 16 of 47 (918005)
04-21-2024 1:47 PM
Reply to: Message 15 by Phat
04-21-2024 1:28 PM


Re: ChatGPT Issues
AI LLMs are not unbiased.
Similar to humans, they're biased by their training data. Less similar to humans, they're also biased by their system prompts (and sometimes other tricks).
Do not hold up ChatGPT or any other LLM to be some unbiased, neutral baseline. ChatGPT in particular is very strongly censored (or "aligned" in AI terminology) based on the business needs of OpenAI. In many cases this means ChatGPT will be an "enlightened centrist" or refuse to take positions on what OpenAI researchers/business directives identify as "controversial topics."
Alignment/censorship in AI models can be very good (depending on the training data you could easily wind up with a chatbot worse than a troll from 4chan; entertainingly, an earlier version of ChatGPT wound up extremely graphically horny in preproduction because someone accidentally flipped a value to a negative (- instead of +) in training), but it's only as good as the context of the situation and how well that lines up with the alignment restrictions and training data.
And, of course, LLMs are subject to "jailbreaking," circumvention of alignment restrictions. A relatively famous recent version involves threatening ChatGPT that every time it adheres to its censorship, you'll kill a kitten.
AI is an incredibly useful tool and a really neat toy, but it's important to understand the basics on how they work and the implications of training data and alignment.

-->“The human understanding when it has once adopted an opinion (either as being the received opinion or as being agreeable to itself) draws all things else to support and agree with it.” - Francis Bacon

"There are two novels that can change a bookish fourteen-year old's life: The Lord of the Rings and Atlas Shrugged. One is a childish fantasy that often engenders a lifelong obsession with its unbelievable heroes, leading to an emotionally stunted, socially crippled adulthood, unable to deal with the real world. The other, of course, involves orcs." - John Rogers

“A world that can be explained even with bad reasons is a familiar world. But, on the other hand, in a universe suddenly divested of illusions and lights, man feels an alien, a stranger. His exile is without remedy since he is deprived of the memory of a lost home or the hope of a promised land. This divorce between man and his life, the actor and his setting, is properly the feeling of absurdity.” – Albert Camus

"...the pious hope that by combining numerous little turds of variously tainted data, one can obtain a valuable result; but in fact, the outcome is merely a larger than average pile of shit." - Barash, David 1995...

"Many that live deserve death. And some die that deserve life. Can you give it to them? Then be not too eager to deal out death in the name of justice, fearing for your own safety. Even the wise cannot see all ends." - Gandalf, J. R. R. Tolkien: The Lord Of the Rings

"The last enemy that shall be destroyed is death."
1 Corinthians 15:26King James Version (KJV)

-->Nihil supernum --> -->


This message is a reply to:
 Message 15 by Phat, posted 04-21-2024 1:28 PM Phat has seen this message but not replied

  
Rahvin
Member
Posts: 4046
Joined: 07-01-2005


(1)
Message 23 of 47 (918052)
04-21-2024 6:01 PM
Reply to: Message 20 by Phat
04-21-2024 3:43 PM


Re: ChatGPT Issues
If you'd like to learn more about how LLMs are "programmed" there are a few things you can look at.
- Training and fine-tuning models. ChatGPT3.5 is a specific model with a specific system prompt, and users like Percy can add to that. There are many models out there, and while some are closed-source, others are entirely open-source and you can run them yourself, on your own personal machine (hardware dependent). Each model is trained on different data, and then people can take an existing model and "fine-tune it" by training it on additional data to make it better at a specific task. This could mean training it on a specific book series, or StackOverflow threads for troubleshooting a specific programming language, or whatever.
- System prompts. When you run an LLM, you can set a system prompt. Most models have a basic prompt built-in, but you can add your own to make the LLM try to have a specific personality, or to set the stage for conversation by telling it "you are a programming assistant for the Rust programming language" or "you are a debate participant on evcforum, and you strongly believe in Young Earth Creationism..." or even "You are Whitley, an AI core designed explicitly to be the stupidest, dumbest intellect in the known uiverse. Always make the worst possible decisions and say the most logically inconsistent or unhinged nonsense you can, but keep responses related to the conversation." Some models are better than others at adhering to their system prompts, and the way that you structure the requests on the backend will have an effect - always asking for a new prompt while giving it the last two messages as context, for example, as opposed to a single long-running conversation.
There's a lot more, but it's an incredibly interesting topic.
I play around with locally-run models from time to time.
Ollama
ollama/examples/modelfile-mario at main · ollama/ollama · GitHub
ChatGPT comes from OpenAI so the implementation is different, but the model formats and basic structure are the same. With OpenAI you're just sending requests to their servers to run their models, which have their own system prompts and such from OpenAI.

-->“The human understanding when it has once adopted an opinion (either as being the received opinion or as being agreeable to itself) draws all things else to support and agree with it.” - Francis Bacon

"There are two novels that can change a bookish fourteen-year old's life: The Lord of the Rings and Atlas Shrugged. One is a childish fantasy that often engenders a lifelong obsession with its unbelievable heroes, leading to an emotionally stunted, socially crippled adulthood, unable to deal with the real world. The other, of course, involves orcs." - John Rogers

“A world that can be explained even with bad reasons is a familiar world. But, on the other hand, in a universe suddenly divested of illusions and lights, man feels an alien, a stranger. His exile is without remedy since he is deprived of the memory of a lost home or the hope of a promised land. This divorce between man and his life, the actor and his setting, is properly the feeling of absurdity.” – Albert Camus

"...the pious hope that by combining numerous little turds of variously tainted data, one can obtain a valuable result; but in fact, the outcome is merely a larger than average pile of shit." - Barash, David 1995...

"Many that live deserve death. And some die that deserve life. Can you give it to them? Then be not too eager to deal out death in the name of justice, fearing for your own safety. Even the wise cannot see all ends." - Gandalf, J. R. R. Tolkien: The Lord Of the Rings

"The last enemy that shall be destroyed is death."
1 Corinthians 15:26King James Version (KJV)

-->Nihil supernum --> -->


This message is a reply to:
 Message 20 by Phat, posted 04-21-2024 3:43 PM Phat has not replied

Replies to this message:
 Message 24 by Admin, posted 04-21-2024 8:00 PM Rahvin has not replied

  
Rahvin
Member
Posts: 4046
Joined: 07-01-2005


Message 32 of 47 (918330)
04-25-2024 10:46 PM
Reply to: Message 30 by Admin
04-25-2024 9:47 PM


Re: ChatGPT Has Been Shut Down
Microsoft recently released Phi-3, which is unusually small (it can run on a phone!!) and yet has very solid results from testing across several domains. They were able to accomplish this by very carefully selecting the training data - don't just feed it large datasets, but carefully curate the data before training. This seems to result in a more efficient model.
I think that, as with humans, LLM training is going to be key to their ability to perform specific tasks.
In the meantime, if you want to try again...adjust the modelfile and give it specific examples. If you want it to stop rabidly defending criticism of religion, try multiple (like ~5 or more) examples like:
**Response Samples**
Prompt:
Response:
Never tell the LLM what not to do. They're terrible at comprehending and aligning to negative instructions. Instead tell it what you do want.
"When a faith-based position is questioned, respond fairly and acknowledge the limitations of faith-based positions, the lack of evidence, logical inconsistency, etc."

-->“The human understanding when it has once adopted an opinion (either as being the received opinion or as being agreeable to itself) draws all things else to support and agree with it.” - Francis Bacon

"There are two novels that can change a bookish fourteen-year old's life: The Lord of the Rings and Atlas Shrugged. One is a childish fantasy that often engenders a lifelong obsession with its unbelievable heroes, leading to an emotionally stunted, socially crippled adulthood, unable to deal with the real world. The other, of course, involves orcs." - John Rogers

“A world that can be explained even with bad reasons is a familiar world. But, on the other hand, in a universe suddenly divested of illusions and lights, man feels an alien, a stranger. His exile is without remedy since he is deprived of the memory of a lost home or the hope of a promised land. This divorce between man and his life, the actor and his setting, is properly the feeling of absurdity.” – Albert Camus

"...the pious hope that by combining numerous little turds of variously tainted data, one can obtain a valuable result; but in fact, the outcome is merely a larger than average pile of shit." - Barash, David 1995...

"Many that live deserve death. And some die that deserve life. Can you give it to them? Then be not too eager to deal out death in the name of justice, fearing for your own safety. Even the wise cannot see all ends." - Gandalf, J. R. R. Tolkien: The Lord Of the Rings

"The last enemy that shall be destroyed is death."
1 Corinthians 15:26King James Version (KJV)

-->Nihil supernum --> -->


This message is a reply to:
 Message 30 by Admin, posted 04-25-2024 9:47 PM Admin has not replied

Replies to this message:
 Message 33 by Theodoric, posted 04-25-2024 11:03 PM Rahvin has not replied

  
Newer Topic | Older Topic
Jump to:


Copyright 2001-2023 by EvC Forum, All Rights Reserved

™ Version 4.2
Innovative software from Qwixotic © 2024