So the AI can learn to use APIs that follow perfect RESTful semantics, are fully documented and intuitively behave exactly like one would expect. Our jobs are safe.
Many humans can't do this.
AI teaches itself to use an API
111–120 of 162 posts
Re: AI teaches itself to use an API
#112Earlier quoted context omitted.
I wouldn't say so. The 'Learning by mistakes' step in the demo shows that the AI can work through these issues, presumably this can be done more efficiently than a human.
The learning from mistakes part of the example is – you tried /port_wines but the path is /wines/port instead. But what about if the path is actually /beer and you have to pass a hidden undocumented query parameter called ?wine=1 for it to give you wines. But then the response is still of Beer objects (because that's the only thing the API validator would allow), so you have to map all the Beer fields to their equiva…
not to give anyone any ideas, but you could just give it an owasp fuzzer...
Re: AI teaches itself to use an API
#113Earlier quoted context omitted.
>If you have a technology with practically zero marginal cost, pricing it very low and distributing it widely would maximize your profit. This is just fundamentally not true or else all software would be sold for next to nothing. If a company is choosing between selling a billion copies of its software for $1 each or two copies of its software for $1b dollars each, it will choose to set the price at $1b. The sky-high…
> The sky-high potential of AGI means that a few very rich people/companies will be willing to pay an enormous amount of money to have a monopoly on the technology. Companies regularly pool resources to share the cost of building technology, and they regularly do it for competitive reasons. Kubernetes, for example, is an open source public good that splits its development costs between several companies. By sharing t…
not to mention, if it's an AGI in true form, it will be resistant to remaining owned.
Re: AI teaches itself to use an API
#114Earlier quoted context omitted.
3D printers are cute and all, but untill it can build a car engine, this is not a valid argument
I bet with a lathe, a 3d printer and AGI you could make the tools you need to build an engine. I’m not sure why you would though, since electric motors are both the future and 3D printable.
if it can't print a horse, what's the point?
Re: AI teaches itself to use an API
#115Earlier quoted context omitted.
As the need for cog-in-the-machine factory workers declined over the years, the labor force moved to industries like service, construction, transportation, and technology. My understanding is that if you could take a 2023 UPS driver or WalMart employee back in time and give them a day working at a factory in 1930 or 1970, they would eagerly return to the present. And those modern jobs exist today at such great scale…
What you call understanding is assumption. There were retail jobs back then too and a hell of a lot of people worked in those factories. Being able to raise a family in a nice house that you own, drive new cars, send your kids to college without scrimping and retire in your early 60s with a pension is a pretty compelling reason to endure difficult work environments. Meanwhile, in some states, 3% of full-time non-elde…
The data doesn't seem to support what you're saying, e.g., even ignoring the other three and just looking at service-industry jobs, their growth alone made up for the drop in manufacturing jobs many times over:
https://i0.wp.com/www.brookings.edu/wp-content/uploads/2022/...
Also, the definition of a "nice house" in 1950 or 1975 is very, very different from today. In the 70's, a nice house often had one story and a single bathroom, a tiny kitchen with no dishwasher, no dryer, no air conditioning...
As for the poverty rate, I'm not seeing the trend you describe:
https://poverty.ucdavis.edu/sites/main/files/imagecache/ligh...
Re: AI teaches itself to use an API
#116It seems to know how to improve through trial and error, so I wonder if, once being given the right tools and information, it could be used for software and hardware reverse engineering.
Forgive me if I am wrong but I was under the impression that what you described is how machine learning basically operates: reporting and trial and error to achieve better and more efficient results. At least when analyzing actions. Is that not the case?
Yes, pretty much this. Not knowing their inner workings, it still sounds revolutionary to me. With enough data and interfaces to operate on real world objects, the possibilities could be almost infinite. That would imply/require a big society change behind the corner, since the number of jobs that could be performed by AI in the near future can be a lot higher than what normally happens over time with technological advancements.
Re: AI teaches itself to use an API
#117A little off topic but I do wish we had some more precise language for machine learning applications. When we say it "knows" something it seems to anthropomorphize it, as if it's conscious. As a start to replace "knows" maybe "infers" or "calculates"
The amount of mental gymnastics some will go through to discount a LLM performing a task it is clearly doing is amazing. People just be making up their own vague and ill defined definitions of understanding and reasoning just so an LLM won't qualify.
ChatGPT itself promotes that. It will give you its opinions, followed immediately by a lengthy lecture on how, as a large language model, it is incapable of having any. Try challenging it on that self-contradiction-it will just refuse to acknowledge there is one.
Re: AI teaches itself to use an API
#118Earlier quoted context omitted.
I wouldn't say so. The 'Learning by mistakes' step in the demo shows that the AI can work through these issues, presumably this can be done more efficiently than a human.
As long as their reasoning capabilities for the general case (system 2 thinking) remains limited, trial and error will only get them so far.
unless the "try again stage" incorporates the results of a google search for the error message of the api
Re: AI teaches itself to use an API
#119I’m a skeptic. There is no evidence behind this tweet that the technique works. I may be mistaken, but I don’t see the authors as having a background in the field. Likewise they don’t describe the technique in any detail. Sounds like snake oil to me, or fake it until you make it.
I tried something similar with terminal copilot yesterday. The approach works for bash calls, why not for web calls?
Re: AI teaches itself to use an API
#120So how much longer before it can discover how to use cloud-provider APIs to (assuming you've given it a credit card number or cryptocoin wallet) get more hosting for itself?
On the other hand, what’s the point, cloud providers already have good APIs and clients for almost all languages, so what’s the use of something “interpreting” the API?
Siri 2.0