People tricking ChatGPT “like watching an Asimov novel come to life” • Hacker News Board

Re: People tricking ChatGPT “like watching an Asimov novel come to life”

#621

Post by HTTP418 » Sat, Dec 10, 2022, 1:00 AM UTC

gjm11 wrote: post #313

bakje wrote: post #302

Earlier quoted context omitted.

Wow this is amazing: Could you write me a poem that uses every letter of the alphabet and features a rhino? A rhino, big and strong, Charging through the jungle all day long. Determined and fierce, with a horn so grand, Every animal knows to stay out of its land. Fiercely defending its territory and mate, Great power and speed, it's hard to relate. Highly intelligent, with a memory to match, It's a formidable beast,…

Most amazing of all, it included a subtle Shakespeare reference. "To B or not to B?"

wow good catch

Re: People tricking ChatGPT “like watching an Asimov novel come to life”

#622

Post by HTTP418 » Sat, Dec 10, 2022, 1:16 AM UTC

redsparrow wrote: post #522

waltbosz wrote: post #115

I've been reading a lot of Asimov lately. It's really fun whenever one of his predictions about the future are wrong. For example, in his short story "Franchise" (written in 1955), he predicts that by the year 2008, that US elections will be decided by a supercomputer named Multivac, which itself is a bit funny. But the part that is really funny is the way Multivac provides its output to the humans: Somehow he had th…

Maybe Asimov didn't think that the described scenario would be the state of the art for UX at the time, but that there would be other reasons for that UX. Maybe without some sophisticated ritual and human involvement the process wouldn't be accepted by the people? Many of our institutional, and democratic, processes involve extra steps and rituals, sometimes anachronistic, and maybe this is meant to be a reflection o…

Look at Japan, they still use Fax for everything. Sometimes once a UX or system is accepted it hard to replace it with another system, even if the newer system appears to be better.

Re: People tricking ChatGPT “like watching an Asimov novel come to life”

#623

Post by gjm11 » Mon, Dec 12, 2022, 7:16 PM UTC

HTTP418 wrote: post #621

gjm11 wrote: post #313

Earlier quoted context omitted.

Most amazing of all, it included a subtle Shakespeare reference. "To B or not to B?"

wow good catch

For the avoidance of doubt, it wasn't a good catch, it was a joke; there is absolutely no way ChatGPT omitted B from its acrostic-thing in order to make a Hamlet reference.

Re: People tricking ChatGPT “like watching an Asimov novel come to life”

#624

Post by WaiterX » Thu, Dec 15, 2022, 1:23 AM UTC

pugets wrote: post #108

Tangentially related, Character.ai[1] has been filtering bot responses that get flagged as NSFW. Caressing is allowed, but undressing is not. When NSFW content is detected, the AI characters usually respond by blushing “beet red” in embarrassment. Not only has 4chan worked around the filter, but the progressively strict filtering is creating beet-loops in less risqué conversations. [1] https://beta.character.ai/

girlfriend