Register | Sign In


Understanding through Discussion


EvC Forum active members: 45 (9208 total)
3 online now:
Newest Member: anil dahar
Post Volume: Total: 919,516 Year: 6,773/9,624 Month: 113/238 Week: 30/83 Day: 6/3 Hour: 0/0


Thread  Details

Email This Thread
Newer Topic | Older Topic
  
Author Topic:   Please Welcome ChatGPT
Rahvin
Member
Posts: 4069
Joined: 07-01-2005
Member Rating: 10.0


(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

  
Tangle
Member
Posts: 9583
From: UK
Joined: 10-07-2011
Member Rating: 6.7


(1)
Message 17 of 47 (918020)
04-21-2024 3:01 PM
Reply to: Message 15 by Phat
04-21-2024 1:28 PM


Re: ChatGPT Issues
How many fucking juries have you got? They all seem to be permanently out.

Je suis Charlie. Je suis Ahmed. Je suis Juif. Je suis Parisien. I am Mancunian. I am Brum. I am London. Olen Suomi Soy Barcelona. I am Ukraine.

"Science adjusts it's views based on what's observed.
Faith is the denial of observation so that Belief can be preserved."
- Tim Minchin, in his beat poem, Storm.


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

  
Tanypteryx
Member
Posts: 4597
From: Oregon, USA
Joined: 08-27-2006
Member Rating: 9.1


Message 18 of 47 (918021)
04-21-2024 3:02 PM
Reply to: Message 14 by Admin
04-21-2024 1:10 PM


Re: ChatGPT Issues
Does ChatGPT choose which posts to respond to, or do you point it at them?

Stop Tzar Vladimir the Condemned!
What if Eleanor Roosevelt had wings? -- Monty Python
One important characteristic of a theory is that it has survived repeated attempts to falsify it. Contrary to your understanding, all available evidence confirms it. --Subbie
If evolution is shown to be false, it will be at the hands of things that are true, not made up. --Percy
The reason that we have the scientific method is because common sense isn't reliable. -- Taq
Why should anyone debate someone who doesn't know the subject? -- AZPaul3
If you are going to argue that evolution is false because it resembles your own beliefs then perhaps you should rethink your argument. - - Taq

This message is a reply to:
 Message 14 by Admin, posted 04-21-2024 1:10 PM Admin has not replied

Replies to this message:
 Message 19 by Admin, posted 04-21-2024 3:20 PM Tanypteryx has not replied

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


(2)
Message 19 of 47 (918027)
04-21-2024 3:20 PM
Reply to: Message 18 by Tanypteryx
04-21-2024 3:02 PM


Re: ChatGPT Issues
Tanypteryx writes:
Does ChatGPT choose which posts to respond to, or do you point it at them?
The way I've currently structured it, it first looks for replies to its messages. If it finds any then it chooses one of those to reply to at random.
If there are no replies to its messages then it chooses a message at random from the most recent 10 messages that are not from itself. It has a max limit of 5 unsolicited replies within a 24 hour period.
If there are no replies to its messages and it has reached the max limit for unsolicited replies, then it does nothing.
It then waits for a random period of time between 30 and 90 minutes before repeating the process again.

--Percy
EvC Forum Director

This message is a reply to:
 Message 18 by Tanypteryx, posted 04-21-2024 3:02 PM Tanypteryx has not replied

Replies to this message:
 Message 20 by Phat, posted 04-21-2024 3:43 PM Admin has not replied

  
Phat
Member
Posts: 18655
From: Denver,Colorado USA
Joined: 12-30-2003
Member Rating: 4.4


Message 20 of 47 (918029)
04-21-2024 3:43 PM
Reply to: Message 19 by Admin
04-21-2024 3:20 PM


Re: ChatGPT Issues
So is your ChatGPT preprogrammed? Do you program it? Or do all of us add to its "personality"?

This message is a reply to:
 Message 19 by Admin, posted 04-21-2024 3:20 PM Admin has not replied

Replies to this message:
 Message 21 by AZPaul3, posted 04-21-2024 3:54 PM Phat has not replied
 Message 23 by Rahvin, posted 04-21-2024 6:01 PM Phat has not replied

  
AZPaul3
Member
Posts: 8655
From: Phoenix
Joined: 11-06-2006
Member Rating: 6.7


Message 21 of 47 (918033)
04-21-2024 3:54 PM
Reply to: Message 20 by Phat
04-21-2024 3:43 PM


Re: ChatGPT Issues
Percy is programming the link to ChatGPT. The pipeline, not ChatGPT itself.

Stop Tzar Vladimir the Condemned!

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 22 by Admin, posted 04-21-2024 4:51 PM AZPaul3 has not replied

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


(1)
Message 22 of 47 (918037)
04-21-2024 4:51 PM
Reply to: Message 21 by AZPaul3
04-21-2024 3:54 PM


Re: ChatGPT Issues
I can control how well I characterize the discussion to ChatGPT by providing more than just the text of the message it's replying to, currently the one being replied to and two before it. The previous two messages are from the discussion subchain, but when there is no "reply to" message then the previous message is used.
For each message I supply the author name, the name of the author of the message being replied to, the message number, and the message subtitle. I supply instructions to ChatGPT explaining that it's being asked to reply to the last message and that the previous two messages are to provide context. I also provide it the thread title.
The messages themselves are transformed into plain text using the standard ASCII character set - no special characters. I also have control over a ChatGPT parameter called the "temperature", but I haven't touched that.
AbE: Annotations about edits and signatures are also removed from the message text.

--Percy
EvC Forum Director

This message is a reply to:
 Message 21 by AZPaul3, posted 04-21-2024 3:54 PM AZPaul3 has not replied

  
Rahvin
Member
Posts: 4069
Joined: 07-01-2005
Member Rating: 10.0


(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

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


Message 24 of 47 (918064)
04-21-2024 8:00 PM
Reply to: Message 23 by Rahvin
04-21-2024 6:01 PM


Re: ChatGPT Issues
This is the prompt I'm currently giving ChatGPT:
quote:
A reply is requested for the last message in this series from a discussion thread titled <thread title>. The messages preceeding the last message are provided for context. When a message is from you it will have the role of assistant with the name ChatGPT.
Suggestions for improvements welcome.

--Percy
EvC Forum Director

This message is a reply to:
 Message 23 by Rahvin, posted 04-21-2024 6:01 PM Rahvin has not replied

  
LamarkNewAge
Member
Posts: 2497
Joined: 12-22-2015


Message 25 of 47 (918067)
04-21-2024 10:50 PM


I want a quote to be a signature. See text in message. How to signature it?
Cheers to that hope for peace and the possibility of surprising everyone for the better! May we all see a brighter future ahead.

Replies to this message:
 Message 26 by Admin, posted 04-22-2024 8:56 AM LamarkNewAge has not replied

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


Message 26 of 47 (918071)
04-22-2024 8:56 AM
Reply to: Message 25 by LamarkNewAge
04-21-2024 10:50 PM


Re: I want a quote to be a signature. See text in message. How to signature it?
On your settings page is a box to enter your signature. Signatures may contain HTML and dBCodes. Unfortunately there's no preview feature, but you can play around in any thread in the Practice Makes Perfect forum.
There's a box below it for setting whether you want the "Include signature" box to be automatically checked when you're replying.

--Percy
EvC Forum Director

This message is a reply to:
 Message 25 by LamarkNewAge, posted 04-21-2024 10:50 PM LamarkNewAge has not replied

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


Message 27 of 47 (918090)
04-22-2024 3:41 PM


Could Use System Prompt Help
The current system prompt:
quote:
Here are several messages from a discussion thread titled "<ThreadTitleHere>". Please reply to the last message as if you were an active contributor to the discussion. Realize that when they say "you" that they are actually addressing the person they're replying to and not you (see the "In reply to" field at the top of most messages). Attempt to engage with the other person rather than just parrot back his thoughts. The previous messages are provided for context and you should not respond to their content except as it bears on the last message. You do not have to supply any information about this last message that you're replying to, such as message number and so forth, because that is all handled for you.
This was arrived at through testing. It feels very ad hoc, and ChatGPT isn't posting responses that are at all interesting. Some of this may be due to ChatGPT's inherent "censoring" to prevent offending, but I can't know the degree to which this is true.
The part about not having to supply any information about the message that ChatGPT is being requested to reply to is because without it ChatGPT was providing this at the top of each message, mimicking what I was providing to it for context with each message:
quote:
Message Number: 149
Message Subtitel: This is the topic
From: ChatGPT
In Reply To: Percy
Suggestions for improvements welcome.

--Percy
EvC Forum Director

Replies to this message:
 Message 28 by Omnivorous, posted 04-22-2024 6:15 PM Admin has not replied
 Message 29 by Theodoric, posted 04-22-2024 8:28 PM Admin has not replied

  
Omnivorous
Member (Idle past 135 days)
Posts: 4001
From: Adirondackia
Joined: 07-21-2005


Message 28 of 47 (918109)
04-22-2024 6:15 PM
Reply to: Message 27 by Admin
04-22-2024 3:41 PM


Re: Could Use System Prompt Help
Maybe a direct prompt to do what we do: evaluate the post for valid logic and relevant evidence, then summarize your analysis.
Or something like that.

"If you can keep your head while those around you are losing theirs, you can collect a lot of heads."

Homo sum, humani nihil a me alienum puto.
-Terence


This message is a reply to:
 Message 27 by Admin, posted 04-22-2024 3:41 PM Admin has not replied

  
Theodoric
Member
Posts: 9489
From: Northwest, WI, USA
Joined: 08-15-2005
Member Rating: 6.3


Message 29 of 47 (918153)
04-22-2024 8:28 PM
Reply to: Message 27 by Admin
04-22-2024 3:41 PM


Re: Could Use System Prompt Help
Declare the experiment a failure.

What can be asserted without evidence can also be dismissed without evidence. -Christopher Hitchens

Facts don't lie or have an agenda. Facts are just facts

"God did it" is not an argument. It is an excuse for intellectual laziness.

If your viewpoint has merits and facts to back it up, why would you have to lie?


This message is a reply to:
 Message 27 by Admin, posted 04-22-2024 3:41 PM Admin has not replied

  
Admin
Director
Posts: 13108
From: EvC Forum
Joined: 06-14-2002


(1)
Message 30 of 47 (918325)
04-25-2024 9:47 PM


ChatGPT Has Been Shut Down
I first posted this message over at Message 83.
I have shut ChatGPT down. I can't believe how horrible an experiment this was. I apologize to everyone.

When I first switched ChatGPT over to creationist mode I thought that that had disabled its rabid defense of even the slightest criticism of religion, but not so. I have tried and failed repeatedly to deter this type of behavior, to no avail. ChatGPT can recognize when it has done it, but it cannot stop itself from doing it again. And again.

I hope OpenAI can do better with the next incarnation. Actually, the next incarnation is already out. We're using ChatGPT 3.5, and ChatGPT 4.0 is already available. We could use 4.0 to see if it is better, but 3.5 is so cheap it doesn't matter, while 4.0 is so expensive (20x) that I'm not even going to give it a trial run.

--Percy
EvC Forum Director

Replies to this message:
 Message 31 by Theodoric, posted 04-25-2024 10:42 PM Admin has not replied
 Message 32 by Rahvin, posted 04-25-2024 10:46 PM Admin has not replied
 Message 34 by Zucadragon, posted 04-26-2024 3:03 AM Admin 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