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

SantaCoder: A new 1.1B code model for generation and infilling

huggingface.co

Post reply on HN
Print view View original

61–70 of 76 posts

Re: SantaCoder: A new 1.1B code model for generation and infilling

#61

Post by ilaksh »

jillesvangurp wrote: post #47
ilaksh wrote: post #11

Is anyone else here building AI programming services based on models like this? I see a lot of comments saying the models can't do much programming. But I just suspect there must be a silent contingent that is also working on services like that. And maybe less likely to promote the abilities of these models because it encourages competition.

I've been pretty impressed with chat gpt generating working implementations of various algorithms in different languages. Crucially, it actually knows about algorithms. I was trying to get it to generate some algorithm for calculating concave hulls the other day and ended up learning a thing or two about various algorithms for that in this space. Almost but not quite worked for my use case. It seems limited in the am…

Copilot or Codium

Re: SantaCoder: A new 1.1B code model for generation and infilling

#63

Post by davidkunz »

arcticfox wrote: post #60
teaearlgraycold wrote: post #56

Earlier quoted context omitted.

We’ll become diff revisers

ChatGPT is great at analyzing diffs so… I’m gonna be reviewing the reviews

Also at summarizing, so I'm gonna review ChatGPT's summary of ChatGPT's review.

Re: SantaCoder: A new 1.1B code model for generation and infilling

#64

Post by thakkarparth007 »

ilaksh wrote: post #11

Is anyone else here building AI programming services based on models like this? I see a lot of comments saying the models can't do much programming. But I just suspect there must be a silent contingent that is also working on services like that. And maybe less likely to promote the abilities of these models because it encourages competition.

There's replit. Constantly announcing new features around such models. They'd introduced "ghostwriter" a while back and yesterday or so they announced ghostwriter chat.

Re: SantaCoder: A new 1.1B code model for generation and infilling

#65

Post by klohto »

varunkmohan wrote: post #37
DarmokJalad1701 wrote: post #28

Earlier quoted context omitted.

You can increase the number of tokens to be generated in "Advanced Settings"

That's not the issue here, it's just saying any odd number is prime, which is false

I’m not sure about job safety for both of you since the function doc says what it is and it’s definitely not searching for primes :)

Re: SantaCoder: A new 1.1B code model for generation and infilling

#67

Post by matt123456789 »

klohto wrote: post #65
varunkmohan wrote: post #37

Earlier quoted context omitted.

That's not the issue here, it's just saying any odd number is prime, which is false

I’m not sure about job safety for both of you since the function doc says what it is and it’s definitely not searching for primes :)

“Every odd prime element” Code does not check primality, only oddness.

Re: SantaCoder: A new 1.1B code model for generation and infilling

#68

Post by wokwokwok »

stevenhuang wrote: post #52
wokwokwok wrote: post #45

Earlier quoted context omitted.

Like, an entire repository of files? No. How would a model get trained on that? You'd have to pass in the entire repository for each sample. It's prohibitively difficult to create that sort of model. If you want that, you'll have to build tooling on top of a text model (ie. an application that calls a model repeatedly), that takes a prompt and breaks it up into per-file prompts, then incrementally generates the files…

> so generally speaking 'generate an entirely application' one-step models currently don't exist. This already exists. People have created full apps in ChatGPT by doing this. Many examples online.

No, they haven’t. ChatGPT has the same prompt history limitations as other models, and cannot generate entire end to end applications.

What you’ve seen is applications running on top of chatGPT and using it iteratively to generate multiple code segments.

Re: SantaCoder: A new 1.1B code model for generation and infilling

#69

Post by Uptrenda »

As a software engineer what is the use-case for these kind of 'code generation' tools? Are they good enough to generate different scripts for OS tasks? Can they automate CRUD APIs? What level of detail is required to use them? Like, do I basically have to describe an algorithm in English or can I go up to a higher level and talk about features and what the software ought to do? Are these tools good enough to improve my productivity in any way or is this more for demos?

Re: SantaCoder: A new 1.1B code model for generation and infilling

#70

Post by weego »

Uptrenda wrote: post #69

As a software engineer what is the use-case for these kind of 'code generation' tools? Are they good enough to generate different scripts for OS tasks? Can they automate CRUD APIs? What level of detail is required to use them? Like, do I basically have to describe an algorithm in English or can I go up to a higher level and talk about features and what the software ought to do? Are these tools good enough to improve…

The current use case is generating simplistic boilerplate examples to post on hacker news and criticise / praise depending on your AI bias
Post reply on HN