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

GitHub cuts AI deals with Google, Anthropic

bloomberg.com

Post reply on HN
Print view View original

561–570 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#561

Post by KronisLV »

0xFACEFEED wrote: post #329
ianbutler wrote: post #311

Earlier quoted context omitted.

I'm actually very curious why AI use is such a bi-modal experience. I've used AI to move multi thousand line codebases between languages. I've created new apps from scratch with it. My theory is the willingness to baby sit and the modality. I'm perfectly fine telling the tool I use its errors and working side by side with it like it was another person. At the end of the day it can belt out lines of code faster than I…

As a programmer of over 20 years - this is terrifying. I'm willing to accept that I just have "get off my lawn" syndrome or something. But the idea of letting an LLM write/move large swaths of code seems so incredibly irresponsible. Whenever I sit down to write some code, be it a large implementation or a small function, I think about what other people (or future versions of myself) will struggle with when interactin…

> I think about what other people (or future versions of myself) will struggle with when interacting with the code.

This feels like the sign of a good developer!

On the other hand, sometimes you just need executable line noise that gets the job done by Thursday so you can ship it and think about refactoring later.

As far as AI code goes, more often than not, it will read as something very generic, which is not necessarily a bad thing. When opening yet another Java CRUD project, I’d be more happy to see someone copy and pasting working code from tutorials or resources online (while it still works correctly), as opposed to seeing people develop bespoke systems on top of what a framework provides for every project.

Re: GitHub cuts AI deals with Google, Anthropic

#562

Post by DeathArrow »

tensor wrote: post #382
chairhairair wrote: post #318

Earlier quoted context omitted.

I have completely the opposite perspective. Unit tests actually need to be correct, down to individual characters. Same goes with API calls. The API needs to actually exist. Contrast that with "high level design, rough outlines". Those can be quite vague and hand-wavy. That's where these fuzzy LLMs shine. That said, these LLM-based systems are great at writing "change detection" unit tests that offer ~zero value (or…

The fact that you think "change detection" tests offer zero value speaks volumes. Those may well be the most important use of unit tests. Getting the function correct in the first place isn't that hard for a senior developer, which is often why it's tempting to skip unit tests. But then you go refactor something and oops you broke it without realizing it, some boring obvious edge case, or the like. These tests are al…

>But then you go refactor something and oops you broke it without realizing it, some boring obvious edge case, or the like

I will start to care when integration tests are failing, because that is an actual bug. Then I will fix the bug and move over.

Re: GitHub cuts AI deals with Google, Anthropic

#563

Post by 71bw »

patrickk wrote: post #520
eru wrote: post #458

Earlier quoted context omitted.

I had the opposite experience lately: I was helping translate some UI text for a website from English to German, my mother tongue. I found that usually the machine came up with better translations than me.

English and German are EU languages. Russian is not. The EU maintains a large translation service to translate most EU official texts into all EU languages. So Google Translate is using that to train on. Google gets a free gift from a multinational bureaucracy and gets to look like a smart company in the process. This is also why English-Mandarin is often poorly translated, in my opinion.

>This is also why English-Mandarin is often poorly translated, in my opinion.

Shockingly, this is something that Yandex Translate absolutely excels at.

Re: GitHub cuts AI deals with Google, Anthropic

#564

Post by DeathArrow »

mattmanser wrote: post #402
tensor wrote: post #382

Earlier quoted context omitted.

The fact that you think "change detection" tests offer zero value speaks volumes. Those may well be the most important use of unit tests. Getting the function correct in the first place isn't that hard for a senior developer, which is often why it's tempting to skip unit tests. But then you go refactor something and oops you broke it without realizing it, some boring obvious edge case, or the like. These tests are al…

I think you've misunderstood what he meant by change detection (not GP, could be wrong). Hard to describe, easy to spot. Some people write tests that are tightly coupled to their particular implementation. They might have tons of setup code in each test. So refactoring means each test needs extensive rewrites. Or there will be loads of asserts that have little to do with the actual thing being tested. These tests usu…

>Some people write tests that are tightly coupled to their particular implementation.

That is not due to people choice but due to what actual code being tested does.

I think integration tests and end to end tests are much better.

Re: GitHub cuts AI deals with Google, Anthropic

#565

Post by arthur_sav »

patrickk wrote: post #520
eru wrote: post #458

Earlier quoted context omitted.

I had the opposite experience lately: I was helping translate some UI text for a website from English to German, my mother tongue. I found that usually the machine came up with better translations than me.

English and German are EU languages. Russian is not. The EU maintains a large translation service to translate most EU official texts into all EU languages. So Google Translate is using that to train on. Google gets a free gift from a multinational bureaucracy and gets to look like a smart company in the process. This is also why English-Mandarin is often poorly translated, in my opinion.

Doesn't that mean it's just inevitable what will happen.

The question is not longer IF machines are capable, the question is WHEN. And the when is no longer decades away.

Re: GitHub cuts AI deals with Google, Anthropic

#566

Post by DeathArrow »

miki123211 wrote: post #302
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

For now, I mostly use AI as a "faster typist". If it wants to complete what I wanted to type anyway, or something extremely similar, I just press tab, otherwise I type my own code. I'd say about 70% of individual lines are obvious enough if you have the surrounding context that this works pretty well in practice. This number is somewhat lower in normal code and higher in unit tests. Another use case is writing one-of…

Yes, for simple boring tasks like converting a JSON to C# classes, it does wonders.

For everything clever it kind of needs baby sitting which doesn't make it faster than writing the code myself.

Even for the glorified use case of writing unit tests it sucks unless the code is very simple with few dependencies.

Re: GitHub cuts AI deals with Google, Anthropic

#567

Post by DeathArrow »

Yodel0914 wrote: post #364
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

I find chatgpt incredibly useful for writing scripts against well-known APIs, or for a "better stackoverflow". Things like "how do I use a cursor in sql" or "in a devops yaml pipeline, I want to trigger another pipeline. How do I do that?". But working on our actual codebase with copilot in the IDE (Rider, in my case) is a net negative. It usually does OK when it's suggesting the completion of a single line, but when…

>"better stackoverflow"

I had asked hard questions on SO that only a human with experience can answer. And I found answers on SO that only a human with experience can answer.

Re: GitHub cuts AI deals with Google, Anthropic

#568

Post by creata »

bastardoperator wrote: post #152
atomic128 wrote: post #62

Earlier quoted context omitted.

Yes. Thank you for saying it. We're watching Microsoft et al. defeat open source. Large language models are used to aggregate and interpolate intellectual property. This is performed with no acknowledgement of authorship or lineage, with no attribution or citation. In effect, the intellectual property used to train such models becomes anonymous common property. The social rewards (e.g., credit, respect) that often mo…

Can you name a company with more OSS projects and contributors? Stop with the hyperbole...

That literally has no bearing on the issue.

Re: GitHub cuts AI deals with Google, Anthropic

#569

Post by DeathArrow »

breckenedge wrote: post #426
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

Tab complete is just one of their proprietary models. I find chat-mode more helpful for refactoring and multi-file updates, even more when I specify the exact files to include.

I think SuperMaven has tab complete and let's you chose the model.

Re: GitHub cuts AI deals with Google, Anthropic

#570

Post by fullstackchris »

chillfox wrote: post #425
girvo wrote: post #412

Earlier quoted context omitted.

The (mostly useless boilerplate “I’m basically just testing my mocks”) tests are being written by AI too these days. Which is mildly annoying as a lot of those tests are basically just noise rather than useful tools. Humans have the same problem, but current models are especially prone to it from what I’ve observed And not enough devs are babysitting the AI to make sure the test cases are useful, even if they’re doin…

There are very few tutorials on how to do testing and I don't think I have ever seen one that was great. Compared to general coding stuff where there's great tutorials available for all the most common things. So I think quality testing is just not in the training data at anywhere close to the quantity needed.

Testing well is both an art and a science, and I mean, just look at the dev community on the topic, some are religious about TDD, some say unit tests only, some say the whole range to e2e etc. etc. hard to have good training data when there is no definition of what is "right" in the first place!
Post reply on HN