Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google CEO says more than a quarter of the company's new code is created by AI

businessinsider.com

Post reply on HN
Print view View original

561–570 of 1001 posts

Re: Google CEO says more than a quarter of the company's new code is created by AI

#561

Post by layer8 »

wahnfrieden wrote: post #501
layer8 wrote: post #336

Earlier quoted context omitted.

One of my concerns is that AI may actually slow innovation in software development (tooling, languages, protocols, frameworks and libraries), because the opportunity cost of adopting them will increase, if AI remains unable to be taught new knowledge quickly.

that is solved via larger contexts

It’s not, unless contexts get as large as comparable training materials. And you’d have to compile adequate materials. Clearly, just adding some documentation about $tool will not have the same effect as adding all the gigabytes of internet discussion and open source code regarding $tool that the model would otherwise have been trained on. This is similar to handing someone documentation and immediately asking questions about the tool, compared to asking someone who had years of experience with the tool.

Lastly, it’s also a huge waste of energy to feed the same information over and over again for each query.

Re: Google CEO says more than a quarter of the company's new code is created by AI

#562

Post by yangcheng »

Having 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 analysis, with LLM 10x productivity for this type of work. At FAANG companies, codebases contain years of business logic, edge cases, and 'not-bugs-but-features.' Engineers know their tech stacks well, and legacy constraints make LLMs less effective, and can generate wrong code that needs to be fixed

Re: Google CEO says more than a quarter of the company's new code is created by AI

#563

Post by unit149 »

fzysingularity wrote: post #162

While I get the MBA-speak of lines-of-code that AI is now able to accomplish, it does make me think about their highly-curated internal codebase that makes them well placed to potentially get to 50% AI-generated code. One common misconception is that all LLMs are the same. The models are trained the same, but trained on wildly different datasets. Google, and more specifically the Google codebase is arguably one of th…

Philosophically, these models are akin to scholars prior to differentiation during their course of study. Throttling data, depending on one's course of study, and this shifting of the period in history step-by-step. Either it's a tit-for-tat manner of exchange that the junior developer is engaged in, when overseeing every edit that an LLM has modified, or I'd assume that there are in-built methods of garbage collection, that another LLM evaluating a hash function partly identifying a block of tokenized internal code would be responsible for.

Re: Google CEO says more than a quarter of the company's new code is created by AI

#564

Post by happyopossum »

morkalork wrote: post #262
fzysingularity wrote: post #162

While I get the MBA-speak of lines-of-code that AI is now able to accomplish, it does make me think about their highly-curated internal codebase that makes them well placed to potentially get to 50% AI-generated code. One common misconception is that all LLMs are the same. The models are trained the same, but trained on wildly different datasets. Google, and more specifically the Google codebase is arguably one of th…

Is the public gemini code gen LLM trained on their internal repo? I wonder if one could get it to cough up propriety code with the right prompt.

> Is the public gemini code gen LLM trained on their internal repo?

Nope

Re: Google CEO says more than a quarter of the company's new code is created by AI

#565

Post by asdfman123 »

atoav wrote: post #537
asdfman123 wrote: post #398

I work for Google, and I just got done with my work day. I was just writing I guess what you'd call "AI generated code." But the code completion engine is basically just good at finishing the lines I'm writing. If I'm writing "function getAc..." it's smart enough to complete to "function getActionHandler()", and maybe suggest the correct arguments and a decent jsdoc comment. So basically, it's a helpful productivity…

So this is basically the google CEO saying "a quarter of our terminal inputs is written by a glorified tab completion"?

Yes. Most AI hype is this bad. They have to justify the valuations.

Re: Google CEO says more than a quarter of the company's new code is created by AI

#566

Post by jamil7 »

layer8 wrote: post #336
_DeadFred_ wrote: post #158

Earlier quoted context omitted.

These tools also require the developer class to that they are intended to replace to continue to do what they currently do (create the knowledge source to train the AI on). It's not like the AIs are going to be creating the accessible knowledge bases to train AIs on, especially for new language extensions/libraries/etc. This is a one and f'd development. It will give a one time gain and then companies will be shocked…

One of my concerns is that AI may actually slow innovation in software development (tooling, languages, protocols, frameworks and libraries), because the opportunity cost of adopting them will increase, if AI remains unable to be taught new knowledge quickly.

You already see this if you use a language outside of Python, JS or SQL.

Re: Google CEO says more than a quarter of the company's new code is created by AI

#567

Post by spockz »

cdchn wrote: post #559
spockz wrote: post #546

Earlier quoted context omitted.

My main gripe with this form of code generation is that is primarily used to generate “leaf” code. Code that will not be further adjusted or refactored into the right abstractions. It is now very easy to sprinkle in regexes to validate user input , like email addresses, on every controller instead of using a central lib/utility for that. In the hands of a skilled engineer it is a good tool. But for the rest it mainly…

>It is now very easy to sprinkle in regexes to validate user input , like email addresses, on every controller instead of using a central lib/utility for that. Some people are touting this as a major feature. "I don't have to pull in some dependency for a minor function - I can just have AI write that simple function for me." I, personally, don't see this as a net positive.

Yes, I have heard similar arguments before. It could be an argument for including the functionality in the standard lib for the language. There can be a long debate about dependencies, and then there is still the benefit of being able to vendor and prune them.

The way it is now just leads to bloat and cruft.

Re: Google CEO says more than a quarter of the company's new code is created by AI

#568

Post by ttul »

tomcam wrote: post #543
alxjrvs wrote: post #517

Earlier quoted context omitted.

In my day to day, this still remains the main way I interact with AI coding tools. I regularly describe it as "The best snippet tool I've ever used (because it plays horseshoes)".

Horseshoes? As in “close enough”?

Or, as in, “Ouch, man! You hit my foot!”

Re: Google CEO says more than a quarter of the company's new code is created by AI

#569

Post by M4v3R »

OnionBlender wrote: post #528
asdfman123 wrote: post #398

I work for Google, and I just got done with my work day. I was just writing I guess what you'd call "AI generated code." But the code completion engine is basically just good at finishing the lines I'm writing. If I'm writing "function getAc..." it's smart enough to complete to "function getActionHandler()", and maybe suggest the correct arguments and a decent jsdoc comment. So basically, it's a helpful productivity…

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.

It probably depends on the tool you use and on the programming language. I use Supermaven autocomplete when writing Typescript and it’s working great, it often feels like it’s reading my mind, suggesting what I would write next myself.
Post reply on HN