Live data from Hacker News

Launch HN: Second (YC W23) – AI bots that add features to web apps

news.ycombinator.com

191–200 of 205 posts

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#191

> There are too many things that humans are writing code for that they shouldn’t be. This includes commodity features and integrations like authentication, forgot-password flows, subscription billing, database setup, CRUD pages, collections, data tables, etc. Human developers should be focused on the code that is special to the product. Bots should take care of the gruntwork. This isn’t grunt work in 99% of web appli…

I foresee this tool being used by people with very little knowledge of programming and operations to blindly release products they don't understand. And business types creating a lot of code for experienced team member to spend time reviewing.

It lowers entry barrier for creating more code of lower average quality. This will only create more grunt work for people who actually understand software development.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#192

Earlier quoted context omitted.

Looking into this right now. I'm looking through logs for your session, and I don't see any unusual accounts names being returned (looks like you're just using one specific one, won't name it here). I will keep looking

So I've looked through logs of your sessions, and the routes you hit, and APIs called, and I still don't see anything unusual. I may be misunderstanding the issue that you faced. I also don't have any client side data for your session (guessing ad blocker). I'd really like to get to the bottom of this one! If you can find some time today to join the Discord so that we can chat for a few minutes, that would be awesome…

Just seen your replies and joined your Discord.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#194

I'm doing this manually now, combining JHipster, ChatGPT and myself. An AI that can see into your Git repo would be very useful, as a helper. So, I support this idea!

So far the really interesting stuff seems to be missing, and isn't really in sight either. I would go with low code tools (JHispter, Bootify.io) and continue from there, for now.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#195
post #188

Earlier quoted context omitted.

I guess there is more complexity than ever too? I feel like the early days of programming might've been actually easier to automate. There was often well designed specs, cleaner design and architectural patterns to follow etc. Not in all cases of course however now, I'm seeing people hoping to god that ChatGPT can write a client for the worlds shittiest XML API because no one else sure as hell wants to do it. So what…

People using AI to generate crap faster is definitely a (short term) risk. And, BTW, not only with code. I read an article stating that in a few years (2-3, can't remember) 80% of content only will be generated by AI. Which would be a disaster. We're already swimming in low quality information and this will only make it worse. OTOH, so much for the idea that people will guide the hand of AI to create better code. As…

There is another way, not all AI training data must be sourced from humans. You can loop a LLM with a compiler and set of tests to run, and it will happily search for solutions on its own. Or it could be connected to a simulator, a game or any real life process and let it learn to optimise a goal that can be measured without human work.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#196

I'm doing this manually now, combining JHipster, ChatGPT and myself. An AI that can see into your Git repo would be very useful, as a helper. So, I support this idea!

So far the really interesting stuff seems to be missing, and isn't really in sight either. I would go with low code tools (JHispter, Bootify.io) and continue from there, for now.

Yup, Bootify.io too!

The Bootify-generated code is easier to read than JHipster's output, too.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#197
lol please be gentle. This is a great idea, but most of these features are tablestakes and likely already implemented in an existing web application. Now, if you had a feature like... create a WebRTC connection API + the UI for full video chat and screensharing with React, that might be interesting.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#198

Earlier quoted context omitted.

Hah. To be honest, 2023 is going to be insane. I'm sure hundreds, if not thousands, of companies are going to emerge which greatly improve the software development process.

I think the software development process is fine, it's all the organizational cruft that slows it down. Your company is a good example of it--you probably didn't use Second to make Second, and being a solo dev had to have been a huge benefit to your velocity. The things that hurt software development are people/process related, and can't be fixed by software, IMO.

What like scrum and agile? Or can you be more specific? Or point me to blog posts about this stuff.

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#199
post #70

While I have been expecting AI to replace programmers for a while, the thing I was never sure about whether this will manifest itself as a business for some companies or whether it means the end of people creating apps altogether. Another risk for building businesses on AI in general is that unlike with software that anyone can build (e.g. for a niche), AI solutions seem to be costly because they require a lot of dat…

Yea, it's going to be interesting to see how this all unfolds. In my opinion, the future of software development looks like this: 1) Human developer instructs A.I. bots to build large volumes of code (like Second) 2) Human developer uses A.I. code assistants in the IDE to make "low level" changes or additions I do not believe that developers or engineers will be replaced. The world needs more software, and there's no…

I see that

> The world needs more software, and there's not enough of us to build it all

... is a paraphrasing of the following from your top-level text

> Moreover, the world needs more software than there are engineers to build it all.

... which I'm very skeptical about. In what sense does the world "need" more software?

What exactly is it that "the world" really needs this additional software for, and is it really software that's missing, or can the same need be fulfilled via other means (e.g. better software, or improved processes)?

And to follow-up on that, if the world does need "more software", is there some level of software that is sufficient? I.e. is there a steady state of software/world, or at least, software/person, or are we "maximizing paperclips"?

Re: Launch HN: Second (YC W23) – AI bots that add features to web apps

#200
post #190

Earlier quoted context omitted.

I just released - https://vocalvoters.com/ It sends an AI generated letter to a congress person in a seconds. Users can edit it, but frankly the results are amazingly good. I bring it up because effectively exactly what you described - a shim on top of 4 APIs. (Code is open sourced, link on the site) The question is how will AI replace what I have? The AI might get better, but ultimately someone has to mail the lette…

> The question is how will AI replace what I have? I think you answered your own question: > Sure the AI systems of the future could theoretically do all that, but it’s still the same work/services. That's it. At the moment, you had to wire together 4 APIs and, as you said, this wouldn't do the job without using (someone else's) AI. So this works as a business/service as long as the AI is not able to handle those 4 A…

I think that’s all fine and good, the app took me very little time to build. BUT I had to test it.

Integrations are more than code (you have to setup physical addresses in this case, transfer money, etc). I do believe an AI will get there, but all that human evaluation will still need to happen.

I personally assume these AI systems will be used as the middleware for a long time. It’ll be hard to enter other spaces because (1) it won’t be something legally the AI company wants to be liable for and (2) it often requires niche semi-documented items.

Much easier for AI companies to let people take the risks. They can then blame that party.

Post reply on HN