Imagine for a second, if you will, being a teacher, and being able to transliterate the text of a lesson, or whole textbook into something written as if the author was some personal super-hero, or mythic legendary being, that the child is specifically currently obsessed with...
Even more, imagine now that all 27 students of your class have a different character they're obsessed with, no problem, just run the query with a list of those 27 character names that those kids will gladly give in an instant! A couple year's work of professional writers done in seconds, now available for being printed on the laser copier and distributed. (i know chatgpt/gpt 3.5 cant do this given a whole long text , but gpt4 can) Anyways, i was just curious to read more experiences/reactions from leonistas about this new AI science that is blooming right now ! :) On Thursday, May 11, 2023 at 11:36:09 PM UTC-4 Félix wrote: > Maybe off-topic, (and sorry in advance if you've seen those kinds of > interactions with chatGPT before) but while I'm finishing translating Leo > to typescript, I now use chatGPT to help move along faster. (while > verifying his answers carefully 'cause he sometimes hallucinates a little > something here and there) > > I sometimes do a little extra interaction with it just for fun, mostly > because i'm still curious about that new wonder of the world that is AI can > do! > > (like thanking him, and treating him like a person, to see how it will > react and answer, or sometimes just acting like it's the super intelligence > they have on the holodeck in startrek, i.e. asking him to role-play or act > as some historical figure... ) > > So i thought you'd find it interesting to see this screenshot (also note > the choice of strings it took to fill in the arrays in the example code > below it's answer too!) > > Félix > [image: screenshot-gpt.png] > > > On Wednesday, April 26, 2023 at 5:09:03 PM UTC-4 tbp1...@gmail.com wrote: > >> An interesting post on the subject, including "alignment": Large >> language model alignment “bias” and cultural consensus theory >> <https://statmodeling.stat.columbia.edu/2023/04/26/llm-alignment-bias-cultural-consensus-theory/> >> . >> >> On Friday, April 21, 2023 at 12:57:32 PM UTC-4 Edward K. Ream wrote: >> >>> On Fri, Apr 21, 2023 at 11:13 AM Thomas Passin <tbp1...@gmail.com> >>> wrote: >>> >>>> And now comes Google: Google's Bard AI Chatbot Can Now Help You Code >>>> and Create Functions For Google Sheets >>>> <https://tech.slashdot.org/story/23/04/21/1353212/googles-bard-ai-chatbot-can-now-help-you-code-and-create-functions-for-google-sheets?utm_source=rss1.0mainlinkanon&utm_medium=feed>. >>>> >>>> *But*: Googlers say Bard AI is “worse than useless,” ethics concerns >>>> were ignored >>>> <https://arstechnica.com/gadgets/2023/04/googlers-say-bard-ai-is-worse-than-useless-ethics-concerns-were-ignored/> >>>> . >>>> >>> >>> There will be false starts. >>> >>> Here's an pithy intro to LLMs and NNs: >>> https://www.youtube.com/watch?v=lnA9DMvHtfI >>> >>> Edward >>> >> -- You received this message because you are subscribed to the Google Groups "leo-editor" group. To unsubscribe from this group and stop receiving emails from it, send an email to leo-editor+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/leo-editor/e216acc7-50e2-4bc4-a36e-8ff92828489an%40googlegroups.com.
