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

661–670 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#661

Post by ta12653421 »

Tainnor wrote: post #596
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…

> I've created new apps from scratch with it. I don't think that "creating new apps from scratch" should be the benchmark. Unless you're doing something very novel, creating a new app/service is rather formulaic. Many frameworks even have templates / generators for that sort of thing. LLMs are maybe just better generators - which is not useless, but it's not where the real complexity of software development lies. The…

Well, for the latter parts they do this already by a perfection of 90%+, i'd say - finally you are glueing together the pieces you get from the LLM.

ClaudeAI Pro rocks, since you can create Projects/Worksapces and put documents into.

Let me ask: How much did you already work with LLM like Claude?

Re: GitHub cuts AI deals with Google, Anthropic

#662

Post by digging »

sdesol wrote: post #322
digging wrote: post #304

Earlier quoted context omitted.

> I think calling it intelligent is being extremely generous ... can't properly recognize that GitHub is capitalized. Wouldn't this make chimpanzees and ravens and dolphins unintelligent too? You're asking it to do a task that's (mostly) easy for humans . It's not a human though. It's an alien intelligence which "thinks" in our language, but not in the same way we do. If they could, specialized AI might think we're u…

Animals are capable of learning. LLMs can not. LLM uses weights that are defined during the training process to decide what to do next. LLM cannot self evaluate based on what it has said. You have to create a new message for it to create a new probability path. Animals have the ability to learn and grow by themselves. LLMs are not intelligent and I don't see how they can be since they just follow the most likely path…

Ok so just to be clear, that's an entirely different and unrelated argument from the one I responded to.

Second, it's wrong. LLMs can learn within their context window. The main issue now is the limited size of their context window; animals have a lifetime of compressed context and LLMs only have approximately one conversation.

Re: GitHub cuts AI deals with Google, Anthropic

#663

Post by goosejuice »

bigstrat2003 wrote: post #268
MuffinFlavored wrote: post #224

Earlier quoted context omitted.

> in practice I’m not noticing a productivity boost. How can this be possible if you literally admit its tab completion is mindblowing? Isn't really good tab completion good enough for at least a 5% producitvity boost? 10%? 20%? Select line of code, prompt it to refactor, verify they are good, accept the changes

> How can this be possible if you literally admit its tab completion is mindblowing? If I had a knife of perfect sharpness which never dulled, that would be mind-blowing. It also would very likely not make me a better cook.

Having a sharp knife will make you far more efficient if you know how to use it in the first place and sharpening knives takes time away from doing the cooking.

This is kind of a wonky analogy though.

Re: GitHub cuts AI deals with Google, Anthropic

#664

Post by imafish »

big_jimmer wrote: post #362
imafish wrote: post #233

Earlier quoted context omitted.

I rarely use the tab completion. Instead I use the chat and manually select files I know should be in context. I am barely writing any code myself anymore. Just sanity checking that the output and “piping” is correct. My productivity (in frontend work at least) is significantly higher than before.

Out of curiosity, how long have you been working as a developer? Just that, in my experience, this is mostly true for juniors and mids (depending on the company, language, product etc. etc.). For example, I often find that copilot will hallucinate tailwind classes that don't exist in our design system library, or make simple logical errors when building charts (sometimes incorrect ranges, rarely hallucinated fields)…

Around 10 years. I also find that claude hallucinates once in a while, but I usually catch it. My main job becomes requesting and reviewing code instead of writing it.

But I don't think it is fair to compare copilot and cursor. I have not been able to gain any significant productivity boost from using copilot (which I have in my Visual Studio proper).

Re: GitHub cuts AI deals with Google, Anthropic

#665

Post by svieira »

Cthulhu_ wrote: post #629
otikik wrote: post #588

Earlier quoted context omitted.

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.

I don't know if you jest but this is likely the next stage, to be released within the next months, that is, AIs doing the first rounds of code reviews. It'll likely be from github / microsoft as they have one of the biggest code review datasets around.

This is already happening - I recently saw a resume which included "Added AI-driven code reviews" as an accomplishment bullet point (the person was working for a large consulting firm).

Re: GitHub cuts AI deals with Google, Anthropic

#666

Post by mu53 »

bushbaba wrote: post #495
gavin_gee wrote: post #386

Earlier quoted context omitted.

cursor is kicking vscode's butt because it has multi models. also MS is hedging bets against OpenAI. that relationship is not easy

Or, anti trust fears.

anti-trust gets a lot harder when ownership can't even be determined

Re: GitHub cuts AI deals with Google, Anthropic

#667

Post by CaptainFever »

GreenWatermelon wrote: post #578
globular-toast wrote: post #541

Earlier quoted context omitted.

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…

But horses were still worse. They shat everywhere.

Re: GitHub cuts AI deals with Google, Anthropic

#668

Post by bgarbiak »

wruza wrote: post #442
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…

A reminder that we basically built cities around the cars, cause they still need fuel, break and drown in the mud. What is your similar plan for LLMs? Analogies always end somewhere, I’m just curious where yours does.

Well, we’ll build all sort of APIs for LLMs to plug into.

Re: GitHub cuts AI deals with Google, Anthropic

#669

Post by rkozik1989 »

Kiro wrote: post #539
javaunsafe2019 wrote: post #387

I don’t know how people can claim such huge success using copilot and such. I also own a subscription and tried to use it for coding but all task from spring boot authentication configuration to aws policies and lambdas it failed horribly. Writing the code myself using proper documentation was the only option. I wonder if false information is written here in the comments section for certain reasons …

It's a completely new skill that you need to learn. My productivity gains are substantial but it comes from experience building multiple applications using LLMs. I feel I learn something new every day and the tooling just gets better and better. > I wonder if false information is written here in the comments section for certain reasons … I find it perplexing that you resort to this instead of other plausible explanat…

What I've found is that the capabilities of LLMs depend on the problem solving skills of the person writing the prompts. If you know exactly what needs to be done and can translate that into step-by-step prompts it can do pretty much anything, but if you're looking for it actually solve 100% of the problem you're going to run into issues. Which is to say you still need to find the solution but you just have the LLM do the monkey work.

Re: GitHub cuts AI deals with Google, Anthropic

#670

Post by sdesol »

digging wrote: post #662
sdesol wrote: post #322

Earlier quoted context omitted.

Animals are capable of learning. LLMs can not. LLM uses weights that are defined during the training process to decide what to do next. LLM cannot self evaluate based on what it has said. You have to create a new message for it to create a new probability path. Animals have the ability to learn and grow by themselves. LLMs are not intelligent and I don't see how they can be since they just follow the most likely path…

Ok so just to be clear, that's an entirely different and unrelated argument from the one I responded to. Second, it's wrong. LLMs can learn within their context window. The main issue now is the limited size of their context window; animals have a lifetime of compressed context and LLMs only have approximately one conversation.

> Ok so just to be clear, that's an entirely different and unrelated argument from the one I responded to.

It honestly made no sense what you were saying so I didn't respond to that directly as I assumed it would be clear from my explanation as to why animals can be intelligent and LLM are not.

> LLMs can learn within their context window.

They don't learn from the context window as much as they use what is in the context window to define a probabilistic path. If you put something in the context window that it was never trained on, it would spit out BS or say it doesn't know.

Post reply on HN