A lot of these features aren't that much work to build. Plugins is Toolformer, you basically tell the model what to emit and then the rest is fairly straightforward plumbing of the sort many coders can do, probably GPT-4 can do a lot of it as well. What is a lot of work and what AI can't do is lining up the partners, QAing the results etc, so the humans are likely working mostly on that.

Also I think it's easy to under-estimate how obvious a lot of this stuff was in advance. They were training GPT-4 last year and the idea of giving it plugins would surely have occurred to them years ago. The enabler here is really the taming of it into chat form and the fine-tuning stuff, not really the specific feature itself.

Is it really that hard? I mean ChatGpt is doing the work (that is how I undestand it). Basically if ChatGpt want's to call an external API, it just gives a specific command and waits for the result, then just simply reads the texts and completes the propt. Sounds like a feature that you could prototype in a week of work.

Of course they fed the entire product roadmap into GPT-4.. jk.

So obviously it's been in the works for a few years now but didn't release to capture the market in a blast. Likely they have GPT-8 already in the making.

They're using GPT5

I find the website to be extremely buggy. Obviously they're prioritizing banging out new features over QA

You don’t have to code anything because it understands human language.

You just tell it “you now have access to search, type [Search] before a query to search it” and it can do it

By not being a stagnant conglomerate, for one.

Alien tech, of course.

They may use GPT-4.