Chad's a super cool guy. I met him at a python conference in Nashville and he was using this big cutter to punch little heart shaped holes in pennies to promote his service gittip (later Gratipay). I had mine for years until it was stolen :/ Glad he's still out there doing good stuff! Chad if you read this you really inspired me that day the way you were so cool with random strangers and genuinely an attentive listener.
It is amazing how software engineers and AI researchers are automating themselves out of their jobs. Sure, it is all good if the revenue generated from automation is used for the good of all people, and if the AIs are aligned/ friendly. But looking at current indications, none of that is going to happen.
AI is just tech. It will enable things, including automation, just like previous generations of tech.
The dawn of the industrial revolution, in which we leveraged machines that were measured in 'horse power' (!) doing far more work than a man (or horse), didn't 'put us out of business' so to speak. Wages skyrocketed. Towards the start of the 20th century wages were high enough that rich folk couldn't afford to keep regular workers around as staff anymore.
I feel it would be naive to think it will just work itself out through capitalism though, it's worth thinking about what impact it will have and whether or not we need some new policies to help society truly capitalize in social value terms, on automation of everything we can automate. GDP is not a measure of how well your society is doing, and with automation we could skyrocket GDP and absolutely tank social measures of wellbeing.
In other words social reforms around how people earn income, or gain housing, food and necessities, might need to happen as we remove more and more jobs.
I'd like to think that as people are freed up they'll be able to do other jobs, but if we plan to automate everything we possibly can that has to eventually be false. Unless everyone's going to be a creative, and even the commercial side of that is starting to be automated. At my work people are already using AI generated images instead of stock photos, and AI generated jingles instead of stock music.
The way I see it the only jobs you are realistically automating (without full on AGI) are the CRUD and pipework jobs which are unambiguously explainable without a lot of context.
The difficulty/complexity in delivering software is mostly on having accurate domain knowledge on the problem you are trying to solve and how users or other machines in that environment interact with said software.
So again, unless we hit a landmark of a very outperforming AGI I think that much of the domain knowledge in many software 'niches' will be out of reach of automation.
That is not to say that many sub-tasks/boilerplate cannot be automated.
But you are missing the point that even a robot could code 90% of the boilerplate and leave it to someone with domain knowledge to check it through and possibly tweak a few bits.
Anything that can be automated will be automated. Software engineers are very expensive so the money is there to be made.
So are doctors, accountants etc.
I don't think its feasible but I'm sure people are working towards it. I'd start with healthcare actually because the West is aging rapidly.
Using the website as a primer, GPT-3 comes up with this:
> Give a TOC for a presentation titled: "How Robb Oat uses Robb Oat to build Robb Oat"
1. Introduction
2. What is Robb Oat?
3. How Robb Oat uses Robb Oat to build Robb Oat
4. Conclusion
> Give 4 speaker note bullet points for each point:
1. Introduction
-Robo Oat is a robot software engineer that reads GitHub issues and submits pull requests.
-It is still in development and currently only fixes code snippets that are linked to in the issue.
-We are going to be discussing how Robb Oat uses Robb Oat to build Robb Oat.
-This will include a demonstration of how to use Robb Oat to fix a code snippet.
2. What is Robb Oat?
-Robb Oat is a robot software engineer that reads GitHub issues and submits pull requests.
-It is still in development and currently only fixes code snippets that are linked to in the issue.
3. How Robb Oat uses Robb Oat to build Robb Oat
-Robb Oat uses Robb Oat to build Robb Oat by trying to fix every GitHub Issue it understands.
-It does this by creating a pull request with an attempted fix.
4. Conclusion
-Robb Oat is still in development and is only able to fix code snippets that are linked to in the issue.
-However, it is a useful tool for those who want to quickly fix small code snippets.
-It is also a good
>If, he thought to himself, such a machine is a virtual impossibility, then it must logically be a finite improbability. So all I have to do in order to make one is to work out exactly how improbable it is, feed that figure into the finite improbability generator, give it a fresh cup of really hot tea ... and turn it on!
I just want to appreciate the name, it was clever (at least for my standard, which, admittedly isn't high), and the name was suggested by DALL-E, which have no context on text input
Yeah it blew me away when DALL-E spit that out on the first try. Both the name and the logo are so perfect, and DALL-E cut the time down from hours if not days or weeks to seconds to get there. At the same time I did iterate on it, I made it two words, Robb Oat, instead of one, Robboat, to make it more relatable and easier to figure out how to pronounce. :^)
Readit News
Here an example issue: https://github.com/robb-oat/server/issues/7
Hit me up chad@zetaweb.com and let's get you a new heart coin. I still have the punch. :D
The dawn of the industrial revolution, in which we leveraged machines that were measured in 'horse power' (!) doing far more work than a man (or horse), didn't 'put us out of business' so to speak. Wages skyrocketed. Towards the start of the 20th century wages were high enough that rich folk couldn't afford to keep regular workers around as staff anymore.
Every phase is different of course.
In other words social reforms around how people earn income, or gain housing, food and necessities, might need to happen as we remove more and more jobs.
I'd like to think that as people are freed up they'll be able to do other jobs, but if we plan to automate everything we possibly can that has to eventually be false. Unless everyone's going to be a creative, and even the commercial side of that is starting to be automated. At my work people are already using AI generated images instead of stock photos, and AI generated jingles instead of stock music.
The difficulty/complexity in delivering software is mostly on having accurate domain knowledge on the problem you are trying to solve and how users or other machines in that environment interact with said software.
So again, unless we hit a landmark of a very outperforming AGI I think that much of the domain knowledge in many software 'niches' will be out of reach of automation.
That is not to say that many sub-tasks/boilerplate cannot be automated.
I don't think its feasible but I'm sure people are working towards it. I'd start with healthcare actually because the West is aging rapidly.
“How Robb Oat uses Robb Oat to build Robb Oat”
> Give a TOC for a presentation titled: "How Robb Oat uses Robb Oat to build Robb Oat"
1. Introduction
2. What is Robb Oat?
3. How Robb Oat uses Robb Oat to build Robb Oat
4. Conclusion
> Give 4 speaker note bullet points for each point:
1. Introduction
-Robo Oat is a robot software engineer that reads GitHub issues and submits pull requests.
-It is still in development and currently only fixes code snippets that are linked to in the issue.
-We are going to be discussing how Robb Oat uses Robb Oat to build Robb Oat.
-This will include a demonstration of how to use Robb Oat to fix a code snippet.
2. What is Robb Oat?
-Robb Oat is a robot software engineer that reads GitHub issues and submits pull requests.
-It is still in development and currently only fixes code snippets that are linked to in the issue.
3. How Robb Oat uses Robb Oat to build Robb Oat
-Robb Oat uses Robb Oat to build Robb Oat by trying to fix every GitHub Issue it understands.
-It does this by creating a pull request with an attempted fix.
4. Conclusion -Robb Oat is still in development and is only able to fix code snippets that are linked to in the issue. -However, it is a useful tool for those who want to quickly fix small code snippets. -It is also a good
>If, he thought to himself, such a machine is a virtual impossibility, then it must logically be a finite improbability. So all I have to do in order to make one is to work out exactly how improbable it is, feed that figure into the finite improbability generator, give it a fresh cup of really hot tea ... and turn it on!
https://sites.google.com/site/h2g2theguide/Index/i/149246
https://github.com/robb-oat/server/issues/45
As you can see it struggles with whitespace.
Runner up was Sobbart Root. :D