A Categorical Archive of ChatGPT Failures · HackerPapers discussions

A Categorical Archive of ChatGPT Failures — mentioned by 13years

Sun, 05 Mar 2023 22:25:55 GMT

> I think my example of a pitfall trap in 4 is sufficient to demonstrate that It is an isolated narrow context. The problem with ASI is there is no such limitations. I addressed this point in the post, but another example would be the Kobayashi Maru Test. Or rather, there has been no system devised that humans have not found a vulnerability. Why would AGI be any different? Alignment/containment must also address the possibility of human exploit of the system as well. So we are back at the beginning in either case. Which means a human could still devise a trap for the AI to leverage its…

Paper and discussion history. A mention is not an endorsement.

A Categorical Archive of ChatGPT Failures — mentioned by 13years

Thu, 02 Mar 2023 15:24:45 GMT

I think it is exposing how naïve it will be to go full speed into full AGI. I personally think AGI Safety in the context of AGI is an oxymoron. Primitive AI is already beyond what we can manage. “The size and complexity of deep learning models, particularly language models, have increased to the point where even the creators have difficulty comprehending why their models make specific predictions. This lack of interpretability is a major concern, particularly in situations where individuals want to understand the reasoning behind a model’s output” from - https://arxiv.org/pdf/2302.03494.pdf

Paper and discussion history. A mention is not an endorsement.

A Categorical Archive of ChatGPT Failures — HN submission

Wed, 08 Feb 2023 08:13:56 GMT

A Categorical Archive of ChatGPT Failures

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.