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

AI in software engineering at Google: Progress and the path ahead

research.google

Post reply on HN
Print view View original

61–70 of 245 posts

Re: AI in software engineering at Google: Progress and the path ahead

#61

Post by sanex »

ks2048 wrote: post #15
cloudking wrote: post #3

The most interesting chart is the "fraction of code created with AI assistance via code completion" trending up to 50%

Seems they need to compare against "dumb" code completion. It seems that even when they are error-free, "large" AI-code-completions are just boilerplate that should be abstracted away in some functions rather than inserted into your code base. On a related note, maybe they should measure number of code characters that can be REMOVED by AI rather than inserted!

Agree with the first sentence. I used to tell people I never type anything more than periods and two or three letters because we already had good autocomplete.

Re: AI in software engineering at Google: Progress and the path ahead

#62

Post by elif »

userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

Not to be rude but I have a hard time relating. Code is its own meaning, and to read it is to understand it. The only way you can use code you don't "understand" is to lack understanding of the language you are using.

Re: AI in software engineering at Google: Progress and the path ahead

#63

Post by RogerL »

bamboozled wrote: post #57
userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

It's a concern I have too, when I get tired, I start to just delegate to co-pilot suggestions as I get desperate, if I didn't have co-pilot, I'd probably just log off for the day. I actually don't really use copilot as I didn't find it that helpful, so I don't really have the problem anymore, but I could see it was a danger. Bit like driving when tired.

I look at is as asking an intern to do some work that I don't have time for. Do I have to check their work? Yes. Might I have to correct and guide the outcome? Again, yes. Am I going to ask them to implement something novel and groundbreaking? Not really, that'd be a disaster unless they are a prodigy. None of that removes my capacity, or any kind of danger.

Re: AI in software engineering at Google: Progress and the path ahead

#64

Post by dietr1ch »

userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

At work I already had teammates who would grant LGTM to code they barely read, but looked fine after reading the description and hopefully also skimming over the code. I feel that this path of least resistance/effort will also apply to things that an LLM spit as those are highly likely to look correct on the surface level.

Re: AI in software engineering at Google: Progress and the path ahead

#65

Post by protortyp »

userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

I felt this on myself as well when I tried to use copilot. Especially when it was later in the day. I still use it for some boilerplate code / building visualizations that feels like boilerplate, but turned it off for any real important code. Atm I find most value in AI in discussing design decisions and to evaluate alternative approaches to mine. There it really had a huge positive impact on my workflow

Re: AI in software engineering at Google: Progress and the path ahead

#66

Post by BOOSTERHIDROGEN »

bdjsiqoocwk wrote: post #11
jprete wrote: post #6

Earlier quoted context omitted.

This isn't a good trend. Reviewers never have the depth of knowledge or understanding of authors.

Also, people shouldn't be allowed to use computers unless they understand how transistors work. If you don't have the depth of knowledge you get nothing.

Although this is well-expressed, I'm left with an unexplainable feeling that I can't quite put my finger on.

Re: AI in software engineering at Google: Progress and the path ahead

#67

Post by replyifuagree »

elif wrote: post #62
userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

Not to be rude but I have a hard time relating. Code is its own meaning, and to read it is to understand it. The only way you can use code you don't "understand" is to lack understanding of the language you are using.

In my almost 30 years in the industry I've run into plenty of people who claimed they knew what code did by reading it, but in practice every single one of them turned out to be only another human flummoxed by unexpected runtime behavior.

Maybe you're the exception!

Re: AI in software engineering at Google: Progress and the path ahead

#69

Post by dilawar »

elif wrote: post #62
userbinator wrote: post #55

As others have mentioned, unless you have a strong conscience and really know what you're doing, it's far too tempting to just accept AI-generated suggestions without really thinking, and IMHO losing that understanding is a dangerous path to go down. AI can only increase quantity, not quality. The industry desperately needs far more of the latter. Related: https://navendu.me/posts/ai-generated-spam-prs/

Not to be rude but I have a hard time relating. Code is its own meaning, and to read it is to understand it. The only way you can use code you don't "understand" is to lack understanding of the language you are using.

I never found my experience that simple. Even at times when I was paying attention which is always in short supply when you need it most.

Libraries are biggest pain point. You don't know what a function really doing unless you have used it before yourself. Docs are not always helpful even when you read them.

Lot of assumptions that may not be totally wrong but not right also. In c++, using [] on a map to access an element is really really dangerous if you haven't read the docs carefully and assumes that it does what you believe it should do.

Re: AI in software engineering at Google: Progress and the path ahead

#70

Post by bitwize »

29athrowaway wrote: post #48

Welcome to the AI pawn shop, where you sell your skills to the AI, you get paid and then your knowledge and skills is sold at cents per token.

You'd be surprised at how many "Make money teaching AIs to code!" job postings there are out there now. Taking "training your replacement" to whole new levels.
Post reply on HN