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

571–580 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#571

Post by DeathArrow »

nsonha wrote: post #525
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,…

> 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.

Re: GitHub cuts AI deals with Google, Anthropic

#572

Post by fullstackchris »

almostdeadguy wrote: post #454
epolanski wrote: post #451

Earlier quoted context omitted.

> Change my mind. Unit, integration, e2e, types and linters would catch most of the things you mention. Not every software is mission critical, often the most important thing is to go as fast and possible and iterate very quickly. Good enough is better than very good in many cases.

> Unit, integration, e2e, types and linters would catch most of the things you mention. Who’s writing those?

Lots of people. For certain types of software (ISO) they are required.

But I'm in the boat (and also experienced many times first hand) all those tests you write will by definition, never test against that first production bug you get :)

Re: GitHub cuts AI deals with Google, Anthropic

#573

Post by fullstackchris »

scubbo wrote: post #482
fullstackchris wrote: post #462

Earlier quoted context omitted.

Finally found a comment down here that I like. I'm also with the notion of tests and also iterating until you get to a solution you like. I also don't see anything particularly "terrifying" that many other comments suggest. At the end of the day, we're engineers that write complex symbols on a 2d canvas, for something that is (ultimately, even if the code being written is machine to machine or something) used for som…

> a bunch of people trying to use a hammer when they needed a screwdriver and then complaining that the hammer didnt work like a screwdriver When it's being sold as a screwdriver, that's hardly their fault.

I'll give you that! Too much of this stuff is sold as the "magic wand" solution... I guess marketing for many products has been like that for a long time...

Re: GitHub cuts AI deals with Google, Anthropic

#574

Post by azangru »

hansonkd wrote: post #367
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…

> The more time I spend in a codebase the better idea I have of what the writer was trying to do. This whole thing of using LLMs to Code reminds me a bit of when Google Translate came out and became popular, right around the time I started studying Russian. Yes, copying and pasting a block of Russian text produced a block of english text that you could get a general idea of what was happening. But translating from en…

> Russian has a lot of ways you can write "compactly" with fewer words than english and have a much more precise meaning of the sentence. (I always likened russian to type-safe haskell and english to dynamic python)

Funny; my experience has been completely the opposite. I've always envied the English language for how compactly and precisely it can express meaning compared to Russian, both because of an immensely rich vocabulary, and because of the very flexible grammar.

I suspect this difference in perception may be due to comparing original texts, especially ones produced by excellent writers or ones that have been polished by generations that use them, to translations, which are almost invariably stylistically inferior to the original: less creative, less playful, less punchy, less succinct. So, if you translate a good Russian writer who is a master of his craft into English, you may feel the inadequacy of the language. Likewise, whenever I try to read translations of English prose into Russian, it reads clumsy and depressingly weak.

Re: GitHub cuts AI deals with Google, Anthropic

#575

Post by fullstackchris »

foobiekr wrote: post #423
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…

The most likely explanation is that the code you are writing has low information density and is stringing things together the same way many existing apps have already done. That isn’t a judgement but trying to use the ai code completion tools for complex systems tasks is almost always a disaster.

Not sure what you mean by "complex systems tasks" but most of the leading models have helped me with writing concurrent go code just fine. Not sure if that counts as "complex" enough. However this was prompting, not completion. Obviously I expect something like copilot to pick the normie non-concurrent implementation

Re: GitHub cuts AI deals with Google, Anthropic

#576

Post by Etherlord87 »

hansonkd wrote: post #367
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…

> The more time I spend in a codebase the better idea I have of what the writer was trying to do. This whole thing of using LLMs to Code reminds me a bit of when Google Translate came out and became popular, right around the time I started studying Russian. Yes, copying and pasting a block of Russian text produced a block of english text that you could get a general idea of what was happening. But translating from en…

I think translating to russian wasn't worse than translating to English because "russian is more compact".

Probably it was worse, because people in charge in Google speak English. It was embarrassing to watch Google conferences where they proposed Google Translate to translate professional products. It's similarly embarrassing watching people proposing chatGPT lightly, because they lack the ability, or probably just don't care to, analyze the problem thoroughly.

Re: GitHub cuts AI deals with Google, Anthropic

#577

Post by Etherlord87 »

KronisLV wrote: post #561
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…

> 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 necess…

> 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.

This is a problem too. ChatGPT enables you to write bad code.

It's like Adobe Flash: flash using websites didn't have to be slow, but it was easy to make a slow website with it.

Re: GitHub cuts AI deals with Google, Anthropic

#578

Post by GreenWatermelon »

globular-toast wrote: post #541
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 funny thing about this comment is there's an increasing number of people beginning to think automobiles were a mistake. They pollute, they're unhealthy, dangerous, cause congestion, but we've built our lives around them and basically addicted to them. LLMs piece together language based on other language they've seen. It's not intelligent, it's just a language tool. Currently we have no idea what will happen once…

Exactly. Cars are horrible, they made everything worse for everyone except the few people with money to buy a car.

Cars produce toxic fumes, air pollution, noise pollution with their engine noises and horns, light pollution with their headlights pointed directly into my fucking eye, consume incredible amounts of resources to function, consume a fuckton of resources for road maintainability waste millions of man-hours in soul-crushing traffic jams, all that for them to be slower than me on my fucking bike inside the city.

Yeah the horse and buggy manufacturers were right, cars were a mistake. We just doubled down on that mistake.

Re: GitHub cuts AI deals with Google, Anthropic

#579

Post by jillesvangurp »

hi_hi wrote: post #496

Every single one of these discussion, at some point, devolves to some version of - is by far the best. In my extensive usage it is consistently outperforms by at least 2x. The difference is night and day. Then the immediate child reply: - What!? You must be holding it wrong. The complete inverse is true for me. I don't know what to make of this contradiction. We're all using the same 2 things right? How can opinions…

Most of the LLM quality discussions have a shelf life measured in weeks. The companies involved are leap frogging each other with model updates and tweaks every few weeks.

Try it yourself. I'm getting a lot of value out of just using chat gpt for coding. It's not without flaws. But I can get it to do a lot of routine stuff quite quickly. What I like about the desktop client is that a prompt is just one alt+space away. I usually just copy paste whatever I'm working on and then ask it to do stuff to it.

There's some art to the prompting and you usually have to nudge it to not be lazy and do the whole thing you asked for. It seems engineers on the other side are working really hard to minimize token usage.

I find it's increasingly the UX that's holding me back, not the model quality. Context windows are now big enough to hold a lot of stuff. But how do you get everything in there that matters? Manually copy pasting together stuff is tedious. I actually wrote a script (well, with some llm help) that flattens things in my repository into a file that I then simply attach to a conversation. Works surprisingly well.

Post reply on HN