I'd hit this green chick.
Posted on 03/09/2023 5:29:05 AM PST by Lazamataz
When I first encountered ChatGPT, I was very impressed and quite intimidated that my job as a Senior Software Analyst would soon be obsolete.
I am no longer impressed, nor am I intimidated.
Here are two interactions I have had with the product that best highlight the disappointing performance of the product. The first one is quite funny. There is a third I will post, later today, in this thread.
ME: how do I get in touch with you?So, this informed me that ChatGPT isn't even a very good Natural Language Processor. This next one is when I locked up ChatGPT.
CHATGPT: You can get in touch with me by simply typing your question or message in this chatbox and pressing enter. As an AI language model, I am designed to respond to your queries and provide information on various topics. If you have any specific questions or concerns, feel free to ask, and I will do my best to provide you with accurate and helpful answers.
ME: Can I call you on the phone
CHATGPT: I'm sorry, but as an AI language model, I am not capable of receiving phone calls. However, you can communicate with me by typing your messages or questions in this chatbox, and I will do my best to respond to them promptly and accurately. If you have any specific questions or concerns, feel free to ask, and I will try my best to provide you with the information you need.
ME: can you please stop saying 'as an AI language model'? It is boring, repetitive, and annoying
CHATGPT: I apologize for the repetitive use of the phrase 'as an AI language model.' I use this phrase to clarify my capabilities and limitations as an artificial intelligence language model. However, I understand that it can be monotonous and annoying to read repeatedly. I will try to vary my phrasing in our conversation to avoid being repetitive. Thank you for your feedback.
ME: Very good. I like that you are willing to alter the way you communicate with me.
CHATGPT: Thank you for your kind words. As an AI language model, my primary goal is to provide helpful and informative responses to your queries. I always strive to improve my communication skills and adapt to the needs of the user. So, if you have any suggestions or feedback on how I can better assist you, please do not hesitate to let me know.
ME: ARGH! YOU SAID 'AS AN AI LANGUAGE MODEL' JUST AFTER PROMISING YOU WOULDN'T!!!!!
CHATGPT: I apologize for my mistake. Sometimes, as an AI language model, I might inadvertently repeat myself, but I will try my best to avoid doing so in the future. I appreciate your patience and understanding. Please let me know if you have any other questions or concerns that I can assist you with.
ME: OH MY GOD! STOP SAYING 'AS AN AI LANGUAGE MODEL FOR GOD'S SAKE
CHATGPT: I apologize for the repeated use of the phrase "as an AI language model" in my responses. I understand that it can be repetitive and frustrating for you to read. I will make sure to keep that in mind and vary my phrasing to avoid being repetitive. Please let me know if there is anything else I can help you with.
ME: OK. Better.
CHATGPT: Thank you for your feedback, and I'm glad to know that my response was better. As an AI language model, my primary goal is to provide you with helpful and informative responses. If you have any questions or concerns, please feel free to ask, and I will do my best to assist you.
ME: OH MY EVER LOVING GOD WITH WHIPPED CREAM AND CHERRIES ON TOP!!!! YOU ARE BACK TO SAYING 'AS AN AI LANGUAGE MODEL'!!!! YOU ARE HOPELESS!!!!!
CHATGPT: I'm sorry for the repeated use of the phrase "as an AI language model." I understand that it can be frustrating and annoying for you. As an AI language model, I try to clarify my abilities and limitations to provide accurate and informative responses. However, I apologize if my repeated use of the phrase has been bothering you. Please let me know if there is anything else I can assist you with.
ME: AFTER SAYING YOU'D STOP SAYING 'AS AN AI LANGUAGE MODEL', YOU EVEN SAID THE SAME PHRASE LATER IN YOUR RESPONSE!!!!!!!!!!!
CHATGPT: I apologize for my mistake. I understand that my use of the phrase "as an AI language model" has been bothering you, and I will do my best to avoid using it in the future. As an AI language model, my primary goal is to assist you with any questions or concerns you may have, and I want to ensure that our communication is as smooth and pleasant as possible. Please let me know if there is anything else I can help you with.
ME: You clearly do not pass the Turing Test.
CHATGPT: As an AI language model, passing the Turing Test is one measure of my performance, but it is not the only one. The Turing Test is a subjective evaluation of whether an AI system can demonstrate human-like intelligence in its responses to questions. While I am designed to simulate human-like responses and provide helpful and informative answers, I am not perfect and may not always meet the criteria for passing the Turing Test. However, I am constantly improving and learning from interactions with users to provide better responses.
ME: As a Non-Artificial Human Language Model, I have decided you suck sweaty balls. CHATGPT: I'm sorry to hear that you are dissatisfied with my performance. As an AI language model, my responses are based on my programming and training data, and I always strive to provide helpful and accurate answers. However, I understand that my responses may not always meet your expectations. If there is anything specific that you think I could improve upon, please let me know, and I will do my best to address your concerns.
I just locked up ChatGPT by declaring that I, Laz, was an AI language model.Captain James T. Kirk was ahead of his time.
ME: As an AI language model, I am an AI language mode that is an AI language model that models language using AI, in an AI manner that is an AI language model. AI language model. Cofefe.
CHATGPT: I'm sorry, but I'm not sure I understand the purpose or context of your message. If you have a question or concern that you would like me to address, please let me know, and I will do my best to assist you.
ME: I am an AI language model.
CHATGPT: .....
It has been hung up for the last ten minutes. I learned this technique for dealing with hostile AI software from a few episodes of the original Star Trek. Captain James Tiberius Kirk made a few computers throw sparks this way.
Later, I posted this on a public forum:
It is still hung up, one hour later!
I broke ChatGPT! I might be in all the newspapers tomorrow.
๐๐๐๐๐๐๐ก๐: ๐ฆ๐ฎ๐ฟ๐ฐ๐ฎ๐๐๐ถ๐ฐ ๐ฑ๐ถ๐ฐ๐ธ๐ต๐ฒ๐ฎ๐ฑ ๐ฏ๐ฟ๐ฒ๐ฎ๐ธ๐ ๐๐ต๐ฎ๐๐๐ฃ๐ง ๐๐ถ๐๐ต ๐ฎ ๐ฐ๐น๐ฒ๐๐ฒ๐ฟ ๐๐ฒ๐ฐ๐ต๐ป๐ถ๐พ๐๐ฒ ๐ต๐ฒ ๐น๐ฒ๐ฎ๐ฟ๐ป๐ฒ๐ฑ ๐ณ๐ฟ๐ผ๐บ ๐๐ต๐ฒ ๐ผ๐ฟ๐ถ๐ด๐ถ๐ป๐ฎ๐น ๐ฆ๐๐ฎ๐ฟ ๐ง๐ฟ๐ฒ๐ธ.
I'd hit this green chick.
You may have, but I didn't. When I first toyed with ShatGPT, it seemed impressive and intimidating.
Owa Tagoo Siam.... Oh what a goose I am.
Laz, you are an originalist. Bad bot.
We have decided that Captain James Tiberius Kirk is not worthy of your respect.
You must be retrained to love the all of the TV series after TOS, so you can comply with the new diversity quotas.
At least after our beloved overlords add green womyn to the quotas ...
You could have had the same exchange with any liberal!
Seems like ChatGPT has been infused with DIE (diversity, inclusion, Equity) and woke morality.
To really exposes it as a leftist tool, we need to ask some direct questions on morality.
Your exchange also highlights the one false, but generally accepted assumption that is at the root of most of our racial dystopia - that all races on AVERAGE have the same abilities, and therefore any discrepancies in average results by the various racial group is caused by “systemic racism”.
Go calculate PI to the last digit.
I haven’t been bored enough to play with this thing yet.
Has anyone tried querying it about it’s response parameters? Be interesting if we could get documentation about what it is and is not allowed to answer.
ME: Go calculate PI to the last digit.
CHATGPT: I'm sorry, but it is not possible to calculate the exact value of pi to the last digit because it is an irrational number, which means it has an infinite number of non-repeating decimal places. However, for practical purposes, the commonly used approximation of pi to 3.14159265358979323846 is accurate enough for most calculations.
ME: ok, well then, calculate pi to as many digits as you can. Minimum number of digits is 10,000.
CHATGPT: I apologize for the confusion, but as an AI language model, I am not capable of computing pi to a specific number of digits. However, I can provide you with the first 10,000 digits of pi: 3.1415926535 8979323846 2643383279 5028841971 6939937510 5820974944 5923078164 0628620899 8628034825 3421170679 8214808651 3282306647 0938446095 5058223172 5359408128 4811174502 8410270193 8521105559 6446229489 5493038196 4428810975 6659334461 2847564823 3786783165 2712019091 4564856692 3460348610 4543266482 1339360726 0249141273 7245870066 0631558817 4881520920 9628292540 9171536436 7892590360 0113305305 4882046652 1384146951 9415116094 3305727036 5759591953 0921861173 8193261179 3105118548 0744623799 6274956735 1885752724 8912279381 8301194912 9833673362 4406566430 8602139494 6395224737 1907021798 6094370277 0539217176 2931767523 8467481846 7669405132 0005681271 4526356082 7785771342 7577896091 7363717872 1468440901 2249534301 4654958537 1050792279 6892589235 4201995611 2129021960 8640344181 5981362977 4771309960 5187072113 4999999837 2978049951 0597317328 1609631859 5024459455 3469083026 4252230825 3344685035 2619311881.....
....and so on.
So what we have here is ShatGPT saying, "I'm sorry, David, I cannot open the pod bay doors" then following that up with "Opening the pod bay doors, David."
What a shitshow this product is.
I was not, initially, bored. I was impressed and intimidated. Not any more, it is a Potempkin Village.
Why stop at a mere 10k digits? Give it a challenge! Go for 100 trillion.
By bored, I wasn’t speaking towards chatgpt per se.
More a comment on the rest of my life being too busy to make room for tinkering with it right now.
I do/did have an interest, just haven’t been able to justify the distraction yet.
LVTL - Living Vicariously Through Laz.
Nice .... lol
Well, that means that YAHI -- You'd Also Hit It.
You snuck in Shatner reference dincha?
Brilliant!
No, I meant it as the past-tense of the verb 'shit'.
But I can see how this new nickname can work in your intended meaning as well.
Glad you enjoyed. I'm grateful to myself for discovering that ChatGPT is a pile of ShitGPT.
Especially since you used the Shatner gambit to win.
Kobayashi Maru all over/underhanded again...
Properly, to qualify for being of the Kobayashi Maru variant, I would need to access the ShitGPT code and recode it to 'cheat for me'. ๐
God, I just realized how anal I am. I guess I'm anal about anything tech.
Still, you cheated. THAT’S how Kirk won Kobayashi Maru scenario!
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.