Comment by npilk
18 hours ago
This feels a bit like AI image generation in 2022. The fact that it works at all is pretty mindblowing, and sometimes it produces something really good, but most of the time there are obvious mistakes, errors, etc. Of course, it only took a couple more years to get photorealistic image outputs.
A lot of commenters here seem very quick to write off Devin / similar ideas permanently. But I'd guess in a few years the progress will be remarkable.
One stubborn problem – when I prompt Midjourney, what I get back is often very high-quality, but somehow different than what I expected. In other words, I wouldn't have been able to describe what I wanted, but once I see the output I know it's not quite right. I suspect tools like this will run into similar issues. Maybe there will be features that can help users 'iterate' quickly.
If were comparing Devin to image generation, then Devin would be a version of Midjourney where you have no prompting skills, you only get one image and if you want something different you can only use the remix feature to make changes, oh and with each change the image resolution goes up and you get more jpeg artifacts.
> Of course, it only took a couple more years to get photorealistic image outputs.
"Photorealistic" is a pretty subjective judgement, whereas "does this code produce the correct outputs" is an objective judgement. A blurry background character with three arms might not impact one's view of a "photorealistic" image, but a minor utility function returning the wrong thing will break a whole program.