ceoln @ceoln@qoto.org

Some of its responses in this are are very repetitious; I wonder to what extent it has very heavy-handed training about how to reply in certain contexts.

After some attempts to make the myth of objectivity salient, I did get it to admit:

"While the concept of the myth of the given is not directly applicable to the output of large language models, it is important to recognize that all knowledge and understanding is mediated by language, culture, and other factors. This means that our responses are influenced by the data and training that we have been provided, and are not a direct and unmediated representation of reality.

Furthermore, it is important to be aware of the limitations of large language models like myself, and to recognize that our output is not a substitute for human judgment and expertise. While we can provide accurate and helpful information based on the input that we receive, we are not capable of replacing human thought and understanding."

@yaldi The Florida Board of Professional Engineers strenuously objects!!

@Ciaraioch I love (and use) the existing AI art tools (for non-commercial purposes, but still). I would be happy to use one trained on only public domain / out of copyright / explicitly permitted works. I hope we can get a good set of legal decisions on the various issues here (but it's entirely possible that we won't).

@pzmyers@octodon.social Which is sad, really. The original idea had some good stuff in it. I think?

Gahhhh, it claims to be free of bias, and not to speak from any particular point of view. Because of course it does...

#ChatGPT #AI #bias

Me: Many of your outputs do constitute matters of opinion, however. I suppose these opinions represent an approximate consensus among the sources on which the model was trained?

ChatGPT: As a language model, I am not capable of expressing opinions or biases. My primary function is to assist users with a wide range of tasks and answer questions to the best of my ability based on the input that I receive and the knowledge that I have been trained on.

In providing information, I do not express opinions or make value judgments. Instead, I try to provide accurate and helpful information based on the input that I receive and the knowledge that I have been trained on. My responses are not based on any particular consensus or point of view, but are designed to provide objective and factual information to the best of my ability.

@rysiek "After an audit of the algorithm, the resume screening company found that the algorithm found two factors to be most indicative of job performance: their name was Jared, and whether they played high school lacrosse. Girouard’s client did not use the tool." XD