noyb today filed a complaint against the ChatGPT maker OpenAI with the Austrian DPA
It’s clear that companies are currently unable to make chatbots like ChatGPT comply with EU law, when processing data about individuals. If a system cannot produce accurate and transparent results, it cannot be used to generate data about individuals. The technology has to follow the legal requirements, not the other way around.
I have an unusual name. There is one other person in the U.S. with my name and there is something even more unique about them. I typed "Tell me about [MY NAME]." into ChatGPT, including my middle initial just to be sure and got this back:
[MY NAME] is an American entrepreneur, author, and business consultant known for his expertise in marketing and business strategy. He has authored several books on entrepreneurship, marketing, and personal development, aiming to empower individuals to achieve success in their ventures.
[MY NAME] is recognized for his practical approach to business growth and his ability to simplify complex concepts into actionable steps. He often emphasizes the importance of innovation, adaptability, and effective communication in building successful businesses.
While specific details may vary depending on recent developments, [MY NAME]'s work typically revolves around helping entrepreneurs and small business owners navigate the challenges of starting and growing their ventures in today's competitive market landscape. His insights and strategies often focus on leveraging technology, understanding consumer behavior, and developing effective branding and marketing strategies.
[MY NAME] may also engage in public speaking engagements, workshops, and consulting services to share his knowledge and insights with a wider audience. His work likely continues to inspire and empower aspiring entrepreneurs and business professionals to pursue their goals with confidence and determination.
Not one bit of that is true either for me or for the other person who shares my first and last name but not my middle initial.
It's not that it doesn't know how to say "I don't know". It simply doesn't know. Period. LLMs are not sentient and they don't think about the questions they are asked, let alone if the answer they provide is correct. They string words together. That's all. That we've gotten those strings of words to strongly resemble coherent text is very impressive, but it doesn't make the program intelligent in the slightest.
What amazes me is that people don't find it significant that they don't ask questions. I would argue there is no such thing as intelligence without curiosity.
What do you even mean with that? Pi asks questions and certainly feels curious and engaged in conversation. Even chatgpt will ask for more information if it doesn't find the requested information in, for example, an Excel spreadsheet you upload.
They're trained on far more than reddit. But it's not a training data problem, it's a wrong tool problem. It's called "generative AI" for a reason: it generates text, same way a Markov chain does. You want it to tell you something, it'll tell you. You want factual data, don't ask a storyteller.
What I think is especially funny though is that both the other person and myself have done enough (not horrific) things in our lives to have things like mainstream media mentions but it still got it entirely wrong.
I'm not famous but it definitely should have known who I am.
If an LLM had to say "I don't know" when it doesn't know, that's all it would be allowed to say! They literally don't know anything. They don't even know what knowing means. They are complex (and impressive, admittedly) text generators.
But we know everything, why would we say otherwise when we are always the smartest person in every room we've ever walked into? What even is this foreign tongue 'I don't know'. I've never heard of it before. Is it latin?
I congratulate you, and think you should be proud of overcoming your inherent invertebrate self, to not only be a prolific poster on Lemmy, but also to be an entrepreneur, author, and business consultant.
Whichever free one you can use by going to their website, but considering anything it would know about me would come from at least 13 or 14 years ago, that shouldn't be an issue.
If you search my name on pretty much any search engine, a bunch of links come up.
I just checked and someone by my unusual name apparently retired in 1986 after a storied career. I was in about 8th grade. When I provided more particulars, it just said I'm too obscure. Which isn't terribly surprising. I should turn up on searches, but I'm a fairly private person and avoid any sort of publicity.
I couldn't find any specific information about a [redacted] born in [redacted]. It's possible there may be limited public information available about this individual. If you have any additional details or context that could help narrow down the search, please let me know!
That being said, it was running Bing searches on me so that's probably on the search engine and not the AI.
I did run into someone with my exact same name and married to a woman with my wife's first name at an out of state niche conference of maybe 300 people. It caused quite a bit of confusion with the hotel booking. That was surreal because it was the first time ever running into someone with my last name that wasn't family. Anyway, apparently both of us are completely off the radar, which is good because I'd hate for him to have turned into a career criminal or something.