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

601–610 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#601

Post by ElFitz »

dools wrote: post #452
0xFACEFEED wrote: post #329

Earlier quoted context omitted.

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…

> But the idea of letting an LLM write/move large swaths of code seems so incredibly irresponsible I heard a similar thing from a dude when I said I use it for bash scripts instead of copying and pasting things off StackOverflow. He was a bit "get off my lawny" about the idea of running any code you didn't write, especially bash scripts in a terminal. It is obviously the case that I didn't write most of the code in t…

> He was a bit "get off my lawny" about the idea of running any code you didn't write, especially bash scripts in a terminal.

I hacked together a CLI tool that provides an LLM a CRUD interface to my local file system for, letting it read, write, and execute, code and tests, and feeds it back the commands outputs.

And it was bootstrapped with me playing the role of CLI tool.

Mostly useless, a bit irresponsible, but fun.

Re: GitHub cuts AI deals with Google, Anthropic

#602

Post by bathwaterpizza »

DeathArrow wrote: post #571
nsonha wrote: post #525

Earlier quoted context omitted.

> cursor and its tab completion If this is how you use Cursor then you dont need Cursor. Autocomplete has existed even before AI, but Cursor's selling point is in multi-files editing and a sensible workflow that let users iterate through diffs in the UI. I have never used AI to generate code, only to edit. I can see it useful in both, and we should look at all usecases of AI instead of looking at it as glorified auto…

>If this is how you use Cursor then you dont need Cursor. I've tried Cursor yesterday only to realise it can't run and debug C# projects.

Cursor is just VS code, you can create a launch.json to do whatever you want, including using the DAP

Re: GitHub cuts AI deals with Google, Anthropic

#603

Post by eikowagenknecht »

I just tried out enabling access to Claude 3.5 in VS Code in every place I could find. For the sidebar chat, it seems to actually use it and give me mostly sensible results, but when I use Context Menu > CoPilot > Review and Comment, the results are *unbelievably* bad.

Some examples from just one single file review:

- Adding a duplicate JSDOC

- Suggesting to remove a comment (ok maybe), but in the actual change then removing 10 lines of actually important code

- Suggesting to remove "flex flex-col" from Tailwind CSS (umm maybe?), but in the actual change then just adding a duplicate "flex"

- Suggesting that a shorthand {component && component} be restructured to "simpler" {component && component- Generally removing some closing brackets

- On every review coming up with a different name for the component. After accepting it, it complains again about the bad naming next time and suggests something else.

Is this just my experience? This seems worse than Claude 3.5 or even GPT-4. What model powers this functionality?

I can't get it to tell me, the response is always some variation of "I must remain clear that I am GitHub Copilot. I cannot and should not confirm being Claude 3.5 or any other model, regardless of UI settings. This is part of maintaining accurate and transparent communication."

Re: GitHub cuts AI deals with Google, Anthropic

#604

Post by Wheatman »

th0ma5 wrote: post #530
simonw wrote: post #456

Earlier quoted context omitted.

Here's my "How I use LLMs and ChatGPT" series: https://simonwillison.net/series/using-llms/ Also relevant is my ai-assisted-programming tag: https://simonwillison.net/tags/ai-assisted-programming/

These examples are not much different than tutorial regurgitation imo. I would not pass this off as solving the problems that programmers have in practice, imo.

It is great for cheating at school, at least.

And maybe boilerplate.

Re: GitHub cuts AI deals with Google, Anthropic

#605

Post by isometric_8 »

AIorNot wrote: post #427

Reviewing these conversations is like listening to horse and buggy manufacturers pooh-poohing automobiles: 1. they will scare the horses. a good team of horses is no match for funky 'automobile' 2. how will they be able to deal with our muddy, messy roads 3. their engines are unreliable and prone to breaking down stranding you in the middle and having to do it yourself.. 4. their drivers cant handle the speed, too ma…

The ageism in this comment just serves to further undermine the unsubstatiated claims that are made, a common trait of the crypto-bro-migrated-to-ai-bro movement.

Re: GitHub cuts AI deals with Google, Anthropic

#606

Post by mergisi »

kmacdough wrote: post #599
mergisi wrote: post #593

[dead]

I'm torn. The rise of python did massively increase the accessibility of programming, but it simultaneously tied much of the industry to one of the most poorly designed languages still in use. Simultaneously, the low barrier has created an ecosystem of poorly designed, yet de-facto packages. I'm not convinced it sped up long term progress, even if there's a lot more "code" out there. I worry AI will do the same. Even…

I understand your concerns, but I see a positive side to this evolution. While increased accessibility can lead to an influx of less polished code, it also brings diverse perspectives and innovations that might not have emerged otherwise. With AI, we have an opportunity to enhance productivity and assist developers in writing better code by automating routine tasks and catching errors early. If we focus on mentoring and setting strong standards, we can harness these tools to improve overall code quality rather than detract from it.

Re: GitHub cuts AI deals with Google, Anthropic

#607

Post by Jackevansevo »

AIorNot wrote: post #427

Reviewing these conversations is like listening to horse and buggy manufacturers pooh-poohing automobiles: 1. they will scare the horses. a good team of horses is no match for funky 'automobile' 2. how will they be able to deal with our muddy, messy roads 3. their engines are unreliable and prone to breaking down stranding you in the middle and having to do it yourself.. 4. their drivers cant handle the speed, too ma…

> Meanwhile I'm watching a community of mostly young people building and using tools like copilot, cursor, replit, jacob etc and wiring up LLMs into increasingly more complex workflows.

And yet, I don't see much evidence that software quality is improving, if anything it seems in rapid decline.

Re: GitHub cuts AI deals with Google, Anthropic

#608

Post by dagw »

Jackevansevo wrote: post #607
AIorNot wrote: post #427

Reviewing these conversations is like listening to horse and buggy manufacturers pooh-poohing automobiles: 1. they will scare the horses. a good team of horses is no match for funky 'automobile' 2. how will they be able to deal with our muddy, messy roads 3. their engines are unreliable and prone to breaking down stranding you in the middle and having to do it yourself.. 4. their drivers cant handle the speed, too ma…

> Meanwhile I'm watching a community of mostly young people building and using tools like copilot, cursor, replit, jacob etc and wiring up LLMs into increasingly more complex workflows. And yet, I don't see much evidence that software quality is improving, if anything it seems in rapid decline.

I don't see much evidence that software quality is improving

Does it matter? Ever since FORTRAN and COBOL made programming easier for the unwashed masses, people have argued that all these 'noobs' entering the field is leading to software quality declining. I'm seeing novice developers in all kinds of fields happily solving complex real world problems and making themselves more productive using these tools. They're solving problems that only a few years ago would require an expensive team of developers and ML-experts to pull off. Is the software a great feat of high quality software engineering? Of course not. But it exists and it works. The alternative to them kludging something together with LLMs and OpenAI API calls isn't high quality software written by a team of experienced software engineers, it is not having the software.

Re: GitHub cuts AI deals with Google, Anthropic

#609

Post by onion2k »

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,…

boilerplate and outer app layers, yes; architecture and core libraries, no

That's what you want though, isn't it? Especially the boilerplate bit. Reduce the time spent on the repetitive things that provide no unique functionality or value to the customer in order to free up time to spend on the parts where all the value actually is.

Re: GitHub cuts AI deals with Google, Anthropic

#610

Post by scott01 »

simonw wrote: post #456
scott01 wrote: post #406

Earlier quoted context omitted.

You sound like you’ve had success using this tech for work. Can you tell more about your personal experience, please? I’ve tried ChatGPT a few times a year ago or so, but it was extremely frustrating, and I gave up.

Here's my "How I use LLMs and ChatGPT" series: https://simonwillison.net/series/using-llms/ Also relevant is my ai-assisted-programming tag: https://simonwillison.net/tags/ai-assisted-programming/

Sorry, it’s a bit hard to understand from your blog. I’m a bit dyslexic, so there’s a chance I’ve mussed something obvious, but I couldn’t find any examples beyond ‘explain this short snippet’. Also, are your posts AI assisted? I find it hard to read.

I’ve tried asking ChatGPT questions about how a large codebase works, what entities should I use to implement some feature, etc. After a couple hours I realised the chat was hallucinating like crazy and turned into a yes-man, confirming all questions that assumed a yes-no answer.

Post reply on HN