Open AI and its apps
what it calls GPTs
It’s not hard to think of promising use cases for GPTs. For example, every large company has an intranet with an employee handbook and other official documents. It’s easy to imagine companies creating GPTs that answer new employee questions.
But I worry GPTs will suffer from the same basic discovery problem as plugins.
I disagree. I think of GPTs as apps that anyone can develop. This strikes me as immensely powerful.
For example, I praised Tyler Cowen’s creation of an interactive book. Anyone will soon be able to do that. You just need to create a GPT. No knowledge of APIs or other esoteric coding skills required.
UPDATE: Somebody did.
Tyler Cowen’s GOAT is another example. Authors can upload a book plus some instructions, suddenly you can chat with the book, takes minutes to hours of your time.
The educational possibilities alone write themselves. The process is so fast you can create one of these daily for a child’s homework assignment, or create one for yourself to spend an hour learning about something.
In fact, Tyler or someone else could create a Tyler Cowen app. Pick a large set of representative essays and blog posts by Tyler and use them to create TylerGPT. Anyone can then query TylerGPT to get his take on any issue, new or old.
I could create my essay-grading formulas (once I fine tune them) as a GPT. That would offer my opinion on the style of essays. But I also could create a GPT to offer my take on the substance of essays. I probably could create an Arnold Kling GPT that would give my take on many issues, and not hallucinate by confusing me with someone else.
Maybe every business will have a GPT, just as every business has
I don’t see the process of discovering GPTs as any sort of hurdle. Think of setting up a GPT as like setting up a web site or a newsletter on Substack. How do people find your web site? You tell them about it, they tell other people about it, and Google tells more people about it. By analogy, people will find your GPT in similar ways. There will be a demand for help in finding GPTs, and something will emerge to meet that demand. GPTs will show up in Google searches, if nothing else.
referenced above:
@
@
I’m surprised TBL thinks discovery is a problem.
This strikes me as old school distributed computing thinking. I say this as an old school distributed computing guy.
All you have to do is write a text based description on f what your GPT does.and put it a bunch more fobvious places. Then all the “DiscoverGPT” variants will be able to find it and people just ask them.
In fact, Tyler and you could have TylerDiscovetGPT and ASKDiscoverGPT which simulate your searching and evaluation of GPTs
"In fact, Tyler or someone else could create a Tyler Cowen app. Pick a large set of representative essays and blog posts by Tyler and use them to create TylerGPT. Anyone can then query TylerGPT to get his take on any issue, new or old."
Hasn't this approach been tried, with less than success as a result? I recall reading, from Freddie DeBoer, if I remember correctly, that someone did this with one writer, and ended up with output that directly contradicted the writer's positions on several issues.
There was also the example where a law firm used GPT to draft a filing in a court case, and the GPT cited cases that didn't exist.
I'm sure there are cases where GPT could give terrific results. But, if you're depending on accuracy, it looks like you still need a checker.