GitHub cuts AI deals with Google, Anthropic • Hacker News Board

Re: GitHub cuts AI deals with Google, Anthropic

#581

Post by hmottestad » Wed, Oct 30, 2024, 8:44 AM UTC

fumeux_fume wrote: post #475

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…

Reading this comment is like listening to Tesla in 2014 tell me about how their cars will be driving themselves. Give it 10 years.

Tesla might not have managed to do it, but Waymo had over 7.1 million miles driven by their driverless cars by 2023: https://www.theverge.com/2023/12/20/24006712/waymo-driverles...

I'm still waiting for the future where a robot maid does my dishes, hangs my clothes, tidies and vacuums my apartment while I'm working on my piano skills. But at least I now have a robot vacuum with a camera that avoids whatever toys I forgot to pick up.

Re: GitHub cuts AI deals with Google, Anthropic

#582

Post by pastage » Wed, Oct 30, 2024, 8:52 AM UTC

azangru wrote: post #574

hansonkd wrote: post #367

Earlier quoted context omitted.

> 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…

Translating is an interpretation of the original text. A translated book can be better than the original. But you often need mastery of the language you translate to.

Re: GitHub cuts AI deals with Google, Anthropic

#583

Post by luckydata » Wed, Oct 30, 2024, 8:52 AM UTC

fumeux_fume wrote: post #475

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…

Reading this comment is like listening to Tesla in 2014 tell me about how their cars will be driving themselves. Give it 10 years.

It might not be perfect yet but my huble Model 3 drove me to a doctor appointment all by itself from my driveway last week. I would say it's pretty damn impressive the kind of progress they were able to make.

Re: GitHub cuts AI deals with Google, Anthropic

#584

Post by luckydata » Wed, Oct 30, 2024, 8:54 AM UTC

enumjorge wrote: post #465

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…

I'm not sure why people can't be humble enough to accept that we don't really know what the future will hold. Just because people have underestimated some new technology in the past doesn't mean that will continue to be true for all new technologies. The fact that LLMs currently do not really understand the answers they're giving you is a pretty significant limitation they have. It doesn't make them useless, but it m…

in the current state they are already plenty useful, I don't think it's worth proving mathematically that something can work 100% of the times when 80% is good enough.

Re: GitHub cuts AI deals with Google, Anthropic

#585

Post by davidthewatson » Wed, Oct 30, 2024, 9:00 AM UTC

Solving complex challenges from code to testing of complex systems full-stop is a page from Buchanan and Pirolli, combined:

https://web.mit.edu/jrankin/www/engin_as_lib_art/Design_thin...

https://www.efsa.europa.eu/sites/default/files/event/180918-...

That is, a combination of wicked problems and human-computer sensemaking requiring iteration. Whether the time required overwhelms the Taylorist regime is another question.

Re: GitHub cuts AI deals with Google, Anthropic

#586

Post by JoeyJoJoJr » Wed, Oct 30, 2024, 9:01 AM UTC

Etherlord87 wrote: post #577

KronisLV wrote: post #561

Earlier quoted context omitted.

> 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.

It’s also like Macromedia Flash in that it is a highly creative force, but people who don’t get it or can’t make it work for them will complain.

Re: GitHub cuts AI deals with Google, Anthropic

#587

Post by hmottestad » Wed, Oct 30, 2024, 9:04 AM UTC

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…

They might very well be holding it wrong. Getting decent use out of an LLM requires knowledge, skill and perseverance. It's a pretty new field and everything is improving and changing incredibly fast.

Re: GitHub cuts AI deals with Google, Anthropic

#588

Post by otikik » Wed, Oct 30, 2024, 9:11 AM UTC

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…

Agree that it is a mess.

If I know that someone is using an llm to produce code, I think it is only fair that I use an LLM to review the code too.

If you want me to put the work as a reviewer, you'd better put the work as a writer.

Re: GitHub cuts AI deals with Google, Anthropic

#589

Post by bob1029 » Wed, Oct 30, 2024, 9:14 AM UTC

DeathArrow wrote: post #559

tensor wrote: post #306

Earlier quoted context omitted.

Why aren't you writing unit tests just because AI wrote the function? Unit tests should be written regardless of the skill of the developer. Ironically, unit tests are also one area where AI really does help move faster. High level design, rough outlines and approaches, is the worst place to use AI. The other place AI is pretty good is surfacing api call or function calls you might not know about if you're new to the…

I am kind of starting to doubt about the utility of unit tests. From a theoretical perspective I see the point in writing unit tests. But in practice I rarely seen them being useful. Guy A writes poor logic and sets in stone that poor logic by writing an unit test. Manual testing discovers a bug so guy B has to modify that poor logic and the unit test. I'd rather see the need for integration tests and end to end test…

I've always looked at unit tests as a targeted and often temporary measure.

Once you have a way to do a good integration/e2e test, the results of the constituent unit tests don't provide as much value.

I'd rather run one big complicated thing for real once than hang my hat on a bunch of fake green checkmarks that update every 50 milliseconds.

Re: GitHub cuts AI deals with Google, Anthropic

#590

Post by lucianbr » Wed, Oct 30, 2024, 9:28 AM UTC

photonthug wrote: post #414

geysersam wrote: post #365

Earlier quoted context omitted.

I'll take a stab at changing your mind. AIs are not able to write Redis. That's not their job. AIs should not write complex high performance code that millions of users rely on. If the code does something valuable for a large number of people you can afford humans to write it. AIs should write low value code that just repeats what's been done before but with some variations. Generic parts of CRUD apps, some fraction…

> I'll take a stab at changing your mind. Not the parent but this doesn’t seem mind changing, because what you describe is the normal/boring route to slightly better productivity using new tools without the breathless hype. And the 20% increase you mention of course depends a lot on what you’re doing, so for many types of work you’d be much closer to zero. I’m curious about the claims of “power users” that are talkin…

> Are they fooling themselves, or trying to fool others, or working at jobs where 90% of their work is boilerplate drudgery, or what exactly?

I wonder about this also. Maybe it's just some of each? Clearly some people fool themselves, the AI companies are doing marketing, some people do have boring jobs...