Re:OpenAI announces leadership transition
by howrar on Saturday November 18, 2023 @11:01AM
(#38320943)
Every token is already being generated with all previously generated tokens as inputs. There's nothing about the architecture that makes this hard. It just hasn't been trained on this kind of task.
Re:OpenAI announces leadership transition
by peyton on Saturday November 18, 2023 @08:14PM
(#38327182)
Really? I don’t know of a positional encoding scheme that’ll handle this.
Re:OpenAI announces leadership transition
by haanjiPT on Saturday November 18, 2023 @02:06PM
(#38323144)
The following are a part of my "custom instructions" to chatGPT -
"Please include a timestamp with current date and time at the end of each response.
After generating each answer, check it for internal consistency and accuracy. Revise your answer if it is inconsistent or inaccurate, and do this repeatedly till you have an accurate and consistent answer."
It manages to follow them very inconsistently, but it has gone into something approaching an infinite loop (for infinity ~= 10) on a few occasions - rechecking the last timestamp against current time, finding a mismatch, generating a new timestamp, and so on until (I think) it finally exits the loop by failing to follow instructions.
LLMs are not AIs, but they could be a core component for one.