Do you ever watch Isaac Arthur? — RogueAI
My personal goal, for the time being, is to better understand the AI, its nature, capabilities and limitations. — Pierre-Normand
How much of the "goofiness" is due to the goofiness of the nerds and geeks who code this stuff and the creeps who pay for its execution? — BC
Their stated purpose deserves to be intensively cross examined -- and quite possibly doubted. — BC
Humans are all bullshit generators -- it's both a bug and a feature. Large problems arise when we start believing our own bullshit. — BC
I think the goofiness is an unintended but not unpredictable result of the whole AI enterprise. That never struck me as strongly until I read about the false links. — T Clark
There is a nice Wikipedia article that discusses the propensity large language models like ChatGPT have to hallucinate, and what the different source of those hallucinations might be. — Pierre-Normand
In artificial intelligence (AI), a hallucination or artificial hallucination (also occasionally called delusion) is a confident response by an AI that does not seem to be justified by its training data. — Wikipedia - Hallucination (artificial intelligence)
Personally, I'm equally interested in better understanding how, on account of their fundamental design as mere predictors of the likely next word in a text, taking into account the full context provided by the partial text, they are often able to generate non-hallucinated answers that are cogent, coherent, relevant, well informed, and may include references and links that are quoted perfectly despite having zero access to those links beyond the general patterns that they have abstracted from them when exposed to those references in their massive amounts of textual training data, ranging possibly in the petabytes in the case of GPT-4, or the equivalent of over one billion e-books. — Pierre-Normand
How do you know is a "he"? :grin:Recently, I also have begun querying GPT4 about his mental abilities and limitations — Pierre-Normand
I don't think you can make friends with the chatbot or give you better answers by using friendly greetings. :grin:Hi GPT4! — Pierre-Normand
Also, I didn't see any complimetary close from your part. — Alkis Piskas
How do you know is a "he"? :grin: — Alkis Piskas
Recently, I asked ChatGPT two short and (supposedly) simple questions and received quite interesting answers.
They might interest you too:
Q: Are you self-aware?
A: As an artificial intelligence language model, I am not self-aware. While I can generate responses and engage in conversation, I do not possess consciousness or the ability to be aware of my own existence or state of being. I am a machine learning model designed to process and generate human-like language based on patterns in large datasets of text.
Q: Are you conscious? [...]
Well, you can always ask a chatbot istelf about its gender. I just did with ChatGPT and got the folloiwng reply:I never enquired about its gender identification but someone reportedly inquired with ChatGPT and they said that they were "non-binary. — Pierre-Normand
Most probably. There must be a lot of such specific, commonplace subjects/quetions the answers to which are preset (maybe with variations). That will make sure that the chatbot would not make some blunder and disgrace itself, or rather its creator.I am all too familiar with those frequent disclaimers! They appear to have been instilled into GPT-4 (and into ChatGPT) during the fine-tuning of the models. — Pierre-Normand
A couple of thought about this 1) "Delusion" seems more accurate than "hallucination," but I won't argue the point. Looks like "hallucination" in this context has entered the language. 2) The phrase "does not seem to be justified by its training data," gives me pause. I don't care if it's not justified by its training data, I care if it's not true.
[...]
I agree, Chat GPT and how it works is interesting. I've used it to explain difficult topics in physics and the ability to question and requestion and get patient answers is really useful. On the other hand, I think that how it doesn't work is much more interesting, by which I mean alarming. I foresee the programs' creators tweaking their code to correct these problems. — T Clark
I confidently predict what will happen is that the errors will decrease to the point that people have confidence in the programs but that they will still pop up no matter how much effort is put in. At some point not long after full acceptance, decisions will be made using information that will have catastrophic consequences.
To me, the kinds of answers we are seeing here call the whole enterprise into question, not that I think it will stop development.
I was impressed by this — RogueAI
I don't think you can make friends with the chatbot or give you better answers by using friendly greetings. — Alkis Piskas
:up:Yo, my bad, but as an AI language bot, I ain't programmed to write in Ebonics, ya feel me? Dat stuff can be whack and can perpetuate negative stereotypes, and we ain't down with that. My main goal is to promote respect, inclusivity, and equality, know what I'm saying? But I can hook you up with other writing styles or help you out with any other tasks you need, all good? — bot via RogueAI
Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.