Proto-plumbing is very LLM amenable
Google CEO says more than a quarter of the company's new code is created by AI
671–680 of 1001 posts
Re: Google CEO says more than a quarter of the company's new code is created by AI
#672I'm waiting for some Google developer to say "More than a quarter of the CEOs statements are now created by AI"... ;-)
I'd say most CEO statements are quite useless already, as they're mostly corporate newspeak.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#673Earlier quoted context omitted.
> if this can be accompanied by an increase in software quality That’s a huge “if”, and by your own admission not what’s happening now. > other LLM agents reviewing code, feeding in compile errors, letting other LLM agents interact with the produced code, etc. What a stupid future. Machines which make errors being “corrected” by machines which make errors in a death spiral. An unbelievable waste of figurative and lit…
> What a stupid future. Machines which make errors being “corrected” by machines which make errors in a death spiral. An unbelievable waste of figurative and literal energy. Humans are machines which make errors. Somehow, we got to the moon. The suggestion that errors just mindlessly compound and that there is no way around it, is what's stupid.
> Humans are machines which make errors.
Indeed, and one of the most interesting errors some human machines are making is hallucinating false analogies.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#674Earlier quoted context omitted.
Supermaven is an incredible intellisense. Most code IS trivial and I barely write trivial code anymore. My imports appear instantly, with high accuracy. I have lots of embedded SQL queries and it’s able to guess the structure of my database very accurately. As I’m writing a query the suggested joins are accurate probably 80% of the time. I’m significantly more productive and having to type much less. If this is as go…
I don't think that is the signal that I think most people are hoping for here. When I hear that most code is trivial, I think of this as a language design or a framework related issue making things harder than they should be. Throwing AI or generates at the problem just to claim that they fixed it is just frustrating.
I'm writing software independently, with an extremely barebones framework (just handles routing pretty much) and very lean architecture. Maybe I should re-phrase it, "a lot of characters in the code base are trivial". Imports, function declarations, variable declarations. Is this stuff code/logic? Barely, but it's completely unavoidable. It all takes time and it's now time I rarely have to spend.
Just as an example, I have "service" functions. They're incredibly simple, a higher order function where I can inject the DB handler, user permissions, config, etc. Every time I write one of these I have to import the ServiceDependencies type and declare which dependencies I need to write the service. I now spend close to zero time doing that and all my time focusing on the service logic. I don't see a downside to this.
Most of my business logic is done in raw SQL, which can be complex, but the autocomplete often helps there too. It's not helping me figure out the logic, it's simply cutting down on my typing. I don't know how anyone could be offered "do you want to have type significantly less characters on your keyboard to get the same thing done?" and say "no thanks". The AI is almost NEVER coding for me, it's just typing for me and it's awesome.
I don't care how lean your system is, there will at least be repetition in how you declare things. There will be imports, there will be dependencies. You can remove 90% of this repetitive work for almost no cost...
I've tried to use ChatGPT to "code for me", and I agree with you that it's not a good option if you're trying to do anything remotely complex and want to avoid bugs. I never do this. But integrated code suggestions (with Supermaven, NOT CoPilot) are incredibly beneficial and maybe you should just try it instead of trying to come up with theoretical arguments. I was also a non-believer once.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#675People overestimate faang. There are many talents working there, sure, but a lot of garbage gets pumped into their codebases as well.
>a lot of garbage gets pumped into their codebases
I would imagine it always has.
>Google CEO says more than a quarter of the company's new code is created by AI
It may very well be starting to become apparent anyway :\
Re: Google CEO says more than a quarter of the company's new code is created by AI
#676Earlier quoted context omitted.
Yeah, but he wants people to hear "reduce headcount by 25% if you buy our shit!"
How do you know that? You are creating this false sense of expectations and hype yourself. I am going to argue contrary. If AI increases productivity 2x, it opens up as much new usecases that previously didn't seem worthy to do for its cost. So overall there will just be more work.
> I am going to argue contrary. If AI increases productivity 2x, it opens up as much new usecases that previously didn't seem worthy to do for its cost. So overall there will just be more work.
This is the entire history of the computing industry. We’ve been automating our work away for decades and it just creates more demand.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#677Earlier quoted context omitted.
Do people find these AI auto complete things helpful? I was trying the XCode one and it kept suggesting API calls that don't exist. I spent more time fixing its errors than I would have spent typing the correct API call.
I really really dislike the ones that get in your way. Like I start typing something and it injects random stuff (yes in the auto-complete colors). I have a similar feeling to when you hear your voice back in a phone: completely disabling your thought process. In IntelliJ thankfully you can disable that part of the AI, and keep the part that you trigger it when you want something from it.
> I have a similar feeling to when you hear your voice back in a phone: completely disabling your thought process.
This is a fantastic description of how it disturbs my coding practice which I hadn't been able to put into words. It's like someone is constantly interrupting you with small suggestions whether you want them or not.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#678Earlier quoted context omitted.
I share your sentiment, I've written three apps where I've used language models extensively (a different one for each: ChatGPT, Mixtral and Llama-70B) and while I agree that they where immensely helpful in terms of velocity, there are a bunch of caveats: - it only works well when you write code from scratch, context length is too short to be really helpful for working on existing codebase. - the output code is pretty…
> context length is too short to be really helpful for working on existing codebase. This is kind of true, my approach is I spend a fairly large amount of time copy-pasting code from relevant modules back and forth into ChatGPT so it has enough context to make the correct changes. Most changes I need to make don't need more than 2-3 modules though. > the output code is pretty much always broken in some way, and you n…
> I'd say maybe 60-70% of the code it writes I don't have to touch at all.
...yet. Bugs can take time to surface.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#679Having worked at both FAANG companies and startups, I can offer a perspective on AI's coding impact in different environments. At startups, engineers work with new tech stacks, start projects from scratch, and need to ship something quickly. LLMs can wrtie way more code. I've seen ML engineers build React frontends without any previous frontend experience, flutter developers write 100-line SQL queries for data analys…
It might not quite be there yet, but one key advantage large codebases have that I think LLMs in time will be able to better exploit is the detection of existing patterns - presuming they're consistent - and application to new code doing similar things or to fix bugs in existing code that deviates from the pattern in some way that causes a bug.
It's a different thing to what you're talking about, but it's one way I'd expect to see LLMs contribute a lot to productivity on larger codebases specifically.
Re: Google CEO says more than a quarter of the company's new code is created by AI
#680Earlier quoted context omitted.
I share your sentiment, I've written three apps where I've used language models extensively (a different one for each: ChatGPT, Mixtral and Llama-70B) and while I agree that they where immensely helpful in terms of velocity, there are a bunch of caveats: - it only works well when you write code from scratch, context length is too short to be really helpful for working on existing codebase. - the output code is pretty…
> context length is too short to be really helpful for working on existing codebase. This is kind of true, my approach is I spend a fairly large amount of time copy-pasting code from relevant modules back and forth into ChatGPT so it has enough context to make the correct changes. Most changes I need to make don't need more than 2-3 modules though. > the output code is pretty much always broken in some way, and you n…
> approach is I spend a fairly large amount of time copy-pasting code from relevant modules back and forth into ChatGPT
It can work, but what a terrible developer experience.
> I'd say maybe 60-70% of the code it writes I don't have to touch at all
I used to to write web apps so the ratio was even higher I'd say (maybe 80/90% of the code didn't need any modification) but the app itself wouldn't work at all if I didn't make those 10% changes. And you really need to read 100% of the code because you won't know upfront where those 10% will be.
> The slow typing is definitely a hindrance! Sometimes when it's a big change I lose focus and alt-tab away, like I used to do when building large C++ codebases or waiting for big test suites to run.
Yeah exactly, it's xkcd 303 but with “IA processing the response” instead of “compiling”. Having instant response was a game changer for me in terms of focus hence productivity.
> I don't want to use a faster model that might give me inferior results
As I said earlier, I didn't really feel the difference in quality so the switch was without drawbacks.