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

131–140 of 245 posts

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

#131

Post by 3abiton »

runlevel1 wrote: post #12

Humans have limited RAM, so we have to put our ideas into an external medium that can then be refined. I've been finding AI's suggestions -- even when rather wrong -- help me do that initial step faster. Which, I think, jives with their findings here.

> I've been finding AI's suggestions -- even when rather wrong -- help me do that initial step faster. Which, I think, jives with their findings here.

What's your process? Can you give an example? So far for me, I found them to be most useful using LLMs as code copilot.

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

#132

Post by viking123 »

Auracle wrote: post #78
bitwize wrote: post #47

Today on Facebook I saw a headline: "Marvel Fans Want to See Miley Cyrus as Rogue in the MCU". And I thought to myself: Which Marvel fans? And now... > Just five years later, in 2024, there is widespread enthusiasm among software engineers about how AI is helping write code. Which software engineers?

There are plenty in this post, and I'm one of them. It may or may not be great for job prospects, but as someone who isn't one of you fancy startup/FAANG super programmers it's great for me to be able to ask it design problems, what the 'best' way to do a certain thing is, or tell it "I need a function given x,y, and z that does this and returns this." There are plenty of instances where it doesn't make sense to use…

It's good if you have some domain knowledge and can kind of detect the bullshit there, and also just in cases where there is large amounts of training data. I am in big tech and I use it pretty much every day, mostly in cases where I would have spent a lot of time googling before.

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

#133

Post by czl »

nomel wrote: post #38
runlevel1 wrote: post #12

Humans have limited RAM, so we have to put our ideas into an external medium that can then be refined. I've been finding AI's suggestions -- even when rather wrong -- help me do that initial step faster. Which, I think, jives with their findings here.

First we extended the reach of our perception with language. Then we extended the energy in our calories reserves with crops/livestock. Then we extended the length of our memories with writing. Then we extended the breadth of our thinking with AI?

...

We extend our perception with remote sensors (video, sound).

We extend our muscles with machines.

...

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

#135

Post by endisneigh »

danpalmer wrote: post #101
endisneigh wrote: post #23

Earlier quoted context omitted.

This is not true. You can’t even disable AI entirely in critique (AI suggested edits), not to mention cider. Certain aspects can be disabled but you cannot entirely remove all AI affordances. It’s force feeding. It will eventually all be opt-out. This is obvious to anyone who works at google. Again, same as force feeding of gen AI search

I have AI suggested edits turned off. It's the 4th setting down in the settings menu. AI suggestions in Cider can be disabled. And all of these things are web apps for which googlers have a rich history of creating Chrome extensions to change things they don't like or disagree with. I don't feel it's obvious at all that this will become forced. What would that even mean – you don't get to edit code anymore but can on…

You can turn off giving ai suggestions, not receiving them.

Not all AI affordances in cider can be disabled. There are plenty of people complaining about this on yaqs and buganizer.

> no one is forced to use them so at worst they're a minor UI annoyance.

This attitude is exactly the problem with Google and is why Google’s AI rollout has been terrible thus far. Luckily the stock is still going up, so whatever I guess.

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

#136

Post by AlexandrB »

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/

> AI can only increase quantity, not quality.

Just in time to make every software product eat up even more CPU and RAM to do simple things.

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

#137

Post by Mmskynettio »

jprete wrote: post #6
trybackprop wrote: post #2

From the blog post: > We observe that with AI-based suggestions, the code author increasingly becomes a reviewer, and it is important to find a balance between the cost of review and added value. We typically address the tradeoff with acceptance rate targets. In the past year since GPT-4 came out, I've also found this to be the case. I'm an ML/backend engineer with little experience in frontend development. Yet, I've…

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

I do and i found plenty of issues while doing code review.

But i started to read a lot more code than what i did 10 years ago

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

#138

Post by Majestic121 »

hejdufufjrj wrote: post #113
dr_dshiv wrote: post #106

Half of all code at Google is AI generated?? (See the line chart, reaching 50%)

No, half of new code has at least one character AI generated, something like that.

Half of new characters are AI generated

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

#139

Post by barrkel »

tmpz22 wrote: post #25
cloudking wrote: post #3

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

Question for any Googlers in the thread - do folks speak up if they see flaws in the methodology or approach of this research or is the pressure from the top so strong on this initiative that people hush up?

The code completion is quite smart and one of the bigger advantages Google has now is the monorepo and the knowhow to put together a pipeline of continuous tuning of models to keep them up to date.

The pressure, such that it is, is killing funding for the custom extension for IntelliJ that made it possible to use it with the internal repo.

Cider doesn't have the code manipulation featureset that IntelliJ has, but it's making up for that with deeper AI integration.

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

#140

Post by thomashop »

irrational wrote: post #32
bongodongobob wrote: post #24

Earlier quoted context omitted.

Right because it's impossible for people to learn things themselves. Knowledge must only be passed down by The Gatekeeper. I'm starting to feel like the programming community is just mad things are easier to learn now.

Are they learning? Or are they just accepting the results, as long as it appears to more or less do what they want, and moving on? The danger seems to be code that is syntactically correct and compiles without errors, but is logically incorrect.

One data point:

In our startup we are short on frontend software engineers.

Our project manager started helping with the UI using an IDE (cursor a VS-code fork) with native ChatGPT integration. In the span of six months, they have become very proficient at React.

They had wanted to learn basic frontend coding for multiple years but never managed to pass the initial hurdles.

Initially, they were only accepting suggestions made by ChatGPT and making frequent errors, but over time, they started understanding the code better and actively telling the LLM how to improve/fix it.

Now, I believe they would have the knowledge to build simple functional React frontends without assistance, but the question is why? As a team with an LLM-augmented workflow, we are very productive.

Post reply on HN