ChatGPT can now call Wolfram Alpha

Post by ditchfieldcaleb » Thu, Mar 23, 2023, 7:24 PM UTC

echoer_lyrist wrote: post #107

jonplackett wrote: post #80

Does anyone know how ChatGPT is deciding is should use Wolfram? I’m curious for two reasons 1) previously it didn’t seem to ‘know’ when it was wrong, so it must have some way to detect this now. 2) when there are more (potentially competing competing?) plugins or will be interesting to see how it decides which is the one to use.

There is another post on the front page announcing ChatGPT plugins[0]. The documentation linked in the announcement describes a JSON document that plugin authors post on their website which describe how chatGPT can interact with the plugin. Part of the spec is a prompt which is passed to chatGPT which is injected into the chatGPT session which tells chatGPT how and when to use the plugin. The manifest for the Wolfram…

Post by dudeinjapan » Thu, Mar 23, 2023, 7:27 PM UTC

tpmx wrote: post #37

Robotbeat wrote: post #35

Earlier quoted context omitted.

It needs us as meat robots to maintain the power grid and other industrial infrastructure.

Nicely illustrated in Transcendence (2014). Widely panned on HN back then. I found it smart, perhaps even prescient.

Post by dudeinjapan » Thu, Mar 23, 2023, 7:28 PM UTC

byteware wrote: post #75

tpmx wrote: post #37

Earlier quoted context omitted.

Nicely illustrated in Transcendence (2014). Widely panned on HN back then. I found it smart, perhaps even prescient.

I was so psyched about this movie, but the idea that an AI that can design new quantum processors in seconds, is even remotely challenged by a few humans is just so stupid

Post by dudeinjapan » Thu, Mar 23, 2023, 7:29 PM UTC

logisticpeach wrote: post #121

g9yuayon wrote: post #83

OpenAI is like Google before 2003, dazzling the world with amazing products backed by astonishing technologies that went beyond wild dreams of millions of people. And most importantly, OpenAI kept releasing new features at blazing speed with a few hundred people, just like early days of Google and Microsoft. This reminds me of stark contrast of Google's GSuite and Microsoft Office. Microsoft released new office every…

This is pretty hyperbolic. Great products that were much better than what they replaced or competed with, but "beyond wild dreams of millions of people"? You'd think they cured cancer in 2003 or something...

Post by calf » Thu, Mar 23, 2023, 7:38 PM UTC

superkuh wrote: post #71

gwern wrote: post #18

Earlier quoted context omitted.

And also whenever the next iteration bootstraps off the Wolfram outputs so it no longer has to call Wolfram & can better generalize/learn thanks to it...

Wolfram himself laid out why this is unlikely to happen, https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-... >Or put another way, there’s an ultimate tradeoff between capability and trainability: the more you want a system to make “true use” of its computational capabilities, the more it’s going to show computational irreducibility, and the less it’s going to be trainable. And the more it’s fundamentally…