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

Google Colab will soon introduce AI coding features

blog.google

Post reply on HN
Print view View original

41–50 of 165 posts

Re: Google Colab will soon introduce AI coding features

#41

Post by tudorw »

brigadier132 wrote: post #22
greatpostman wrote: post #4

I really think the current paradigm of literally typing if else logic all day into programs, and then getting paid huge money to do so will go away. Programming is going to be much higher level and accessible, though still complex. It will take five years or so. Edit: My prediction is essentially that: You give it a set of requirements for an api, with edge conditions written in plain English. Test cases are provided…

Here's a different 10-year prediction. AI will become good enough to be useful for programmers but not good enough to run on its own and will remain an assistant. Given that there is a shortage of programmers, more software will be written than ever. More software will beget more software engineers. Because the output of software engineers will rise, each individual software engineer will become more valuable to thei…

Having played a bit with coding with AI I like this view, it's powerful, but context will always be an issue, turning real world problems into working code is a skill in it's own right, that will not change, superpowered yes, for me it's all the 'dull' parts of typing stuff out that I look forward to missing, from an early study on impact in the workplace, using a 2 year study of a call centre, the result was large improvement for less skilled staff as knowledge of best practice from those really excelling at customer service was rapidly propagated to juniors, seniors saw a much smaller increase in performance metrics. Now there is no excuse for me not to get AI to write my comments, a bunch of tests and some API's and database interconnects, etc. I've always taken a modular iterative approach, create a working basic model with a good foundation then extend it keeping it working as I build up to the final deliverable. Tempting just to go and sit in a cave for a couple of months and come back when the tools are a little more refined :)

Re: Google Colab will soon introduce AI coding features

#42

Post by worldsayshi »

anotherpaulg wrote: post #8

(Shamelessly spreading the word about my open source tool) You can do GPT-4 powered coding chats in your terminal today with aider. It's not free in the sense that you need a gpt-4 api key, which openai charges you for. But it's a pretty great way to collaborate with AI on code. https://github.com/paul-gauthier/aider

Neat! This interface look simpler than most alternatives I've seen lately.

Do you know how it deals with source files that are larger than the context window?

Re: Google Colab will soon introduce AI coding features

#43

Post by greatpostman »

beoberha wrote: post #35
greatpostman wrote: post #4

I really think the current paradigm of literally typing if else logic all day into programs, and then getting paid huge money to do so will go away. Programming is going to be much higher level and accessible, though still complex. It will take five years or so. Edit: My prediction is essentially that: You give it a set of requirements for an api, with edge conditions written in plain English. Test cases are provided…

What do you mean by “higher level”? AI code generation tools are extremely useful to people who know how to code, but how is it useful if you can’t understand the code it spits out. They are far from bug free and prompting it to handle complex business logic is tricky. If the higher level paradigm is simply English, then I don’t see it. If something else, I’m curious what you foresee.

You give it a set of requirements for an api, with edge conditions written in plain English. Test cases are provided. And the vanilla api is generated. We aren’t that far from this. It’s going to happen. Complex software will require human coding. But most programmers are in denial about how complex the code they’re writing actually is

Re: Google Colab will soon introduce AI coding features

#44

Post by pphysch »

danwee wrote: post #13
greatpostman wrote: post #4

I really think the current paradigm of literally typing if else logic all day into programs, and then getting paid huge money to do so will go away. Programming is going to be much higher level and accessible, though still complex. It will take five years or so. Edit: My prediction is essentially that: You give it a set of requirements for an api, with edge conditions written in plain English. Test cases are provided…

That's what they thought 50 years ago. Programming is not anymore "mov eax,1" and "int 0x80". Programming nowadays is much more highly accessible than it was 50 years ago... but still only a few (programmers) do it. AI is not going to change that (i.e., nor my manager nor my mother are suddendly going to "program" anything using high-level constructs)

Yeah, generating some Python with Codey is just adding another layer to an already substantial stack.

Natural language is translated into Python which is interpreted as C which was compiled into bytecode which is...

We still need experts at every layer.

Re: Google Colab will soon introduce AI coding features

#45

Post by striking »

cperry wrote: post #29
meghan_rain wrote: post #19

> Democratizing machine learning for everyone: Anyone with an internet connection can access Colab, and use it free of charge. Millions of students use Colab every month to learn Python programming and machine learning. Under-resourced groups everywhere access Colab free of charge, accessing high-powered GPUs for machine learning applications. Ugh, cringe. Just say this is a panic swing at an existential threat (Open…

lol been working on this since 2021; I have a small team and we do our best.

Deep respect for reading the comments and showing up for your team.

Re: Google Colab will soon introduce AI coding features

#49

Post by oli5679 »

I find VS-code running notebooks with Colab plugin installed pretty helpful for this type of thing already.

(1) run notebook in VS-code https://code.visualstudio.com/docs/datascience/jupyter-noteb...

(2) install Github Copilot extension https://marketplace.visualstudio.com/items?itemName=GitHub.c...

and then it can quite often achieve what you want with just a comment or some previous code snippets.

Then if you load in pandas and a DataFrame you want to analyse, it quite often suggests the next stage of your data-analysis work, either right away, as you write the first step in some chain of pandas methods.

Post reply on HN