Hey! I’m the creator of www.autoregex.xyz (@gd3kr on twitter) I originally built it as a small side project in a couple days, I was absolutely not expecting a response this massive. I realise concerns about email and password sign up, and I built it in an hour-ish with firebase auth as a temporary solution to capping the sudden surge in GPT3 requests to the server after the twitter post gained traction. Im working on a better approach to that involving not having to create an account. Otherwise, all suggestions are absolutely welcome. Please tell me how I can make this a better experience for everyone.
So I was talking to a friend about this, and he thought this was a parody because of all the obviously incorrect results you were highlighting in the Twitter thread. Other people have mentioned the \ escapes going missing, but my friend called out https://twitter.com/gd3kr/status/1545495732265766913 as so hilariously wrong that it couldn't have been anything other than a parody.
Is this really a parody, or is it just another example of people not actually reading GPT-3 output carefully enough to notice it's nonsense?
Hey, no it’s not a parody lmao. I shipped it because realised it could have at least some utility while building it. To be fair, the wrong examples would be an oversight on my part, but I thought of them being more of genuine benchmark of what GPT3 was capable of; sort of like an experimental feature. I’m working hard on refining the results by fine tuning DaVinci and getting the output as close to ideal as possible — I think there’s a lot of potential there. In the end, even boosting a user’s productivity marginally is a win in my book, and as a lot of people have pointed out, it’s already doing that to some extent.
