Live data from Hacker News

Demo of an OpenAI language model applied to code generation [video]

twitter.com

91–100 of 158 posts

Re: Demo of an OpenAI language model applied to code generation [video]

#91
post #87

Earlier quoted context omitted.

You still need a programmer to find the bugs. I think it's actually harder to spot and fix a bug, than to write a simple method that involves one.

Programming skills are directly correlated to programmer ability to debug, I will go as far stating; programming is not about writing code, but in ability to find bugs and figure out how to resolve them.

I've always found it easier to debug code I wrote, mostly because I find it the easier to read the code I wrote, since I understand the author's intent.

Re: Demo of an OpenAI language model applied to code generation [video]

#92

So that's basically program synthesis from natural language (ish) specifications (i.e. the comments). I can see this being a useful tool [1]. However, I don't expect any ability for innovation. At best this is like having an exceptionally smart autocomplete function that can look up code snippets on SO for you (provided those code snippets are no longer than one line). That's not to say that it can't write new code,…

I think you are underselling the potential of a model which deeply understand programming. Imagine combining such a model with something like AutoML-Zero: https://arxiv.org/abs/2003.03384 It may not be 'creative', but used as tab-completion, it's not being rewarded or incentivized or used in any way which would expose its abilities towards creating a new sort algorithm.

Re: Demo of an OpenAI language model applied to code generation [video]

#93
post #63
post #18

I had trouble accessing the relevant video snippet even after going through the conference registration, so here's a summary. You can view the demo at https://twitter.com/i/broadcasts/1OyKAYWPRrWKb starting around 29:00. It's Sam Altman demoing a massive Open AI model that was trained on GitHub OSS repos using a Microsoft supercomputer. It's not Intellicode, but the host says that they're working on compressing the m…

Thanks, but it's Sam McCandlish doing the demo (and the project).

I'm confused. Is that not you doing the OpenAI demo around 29:00?

Re: Demo of an OpenAI language model applied to code generation [video]

#94
post #88

Not going to build my hopes up, but looking forward for automated tests generation.

Honestly I think that will be harder for this kind of system than writing this sort of code. It takes a certain kind of creativity to think of ways that code could potentially fail, and it also requires fairly deep understanding of the intent behind a feature.

Re: Demo of an OpenAI language model applied to code generation [video]

#95
I don't see it replacing (or even much augmenting) professional programming any time soon... My predicted use case for this is mostly with non-programmers. They'll be instructed to write in English what they want to be done, and behind the scenes this will attempt to generate code, execute it, and give the results. A fun demo would be writing "Download the recipe on this webpage (paste link) and order the ingredients from Safeway". If it could generate its own billing and shipping storage to remember indefinitely after getting it from the user, then generate the relevant web scraping / web driving or API code for various websites, that'd be pretty sweet.

Re: Demo of an OpenAI language model applied to code generation [video]

#96
post #92

So that's basically program synthesis from natural language (ish) specifications (i.e. the comments). I can see this being a useful tool [1]. However, I don't expect any ability for innovation. At best this is like having an exceptionally smart autocomplete function that can look up code snippets on SO for you (provided those code snippets are no longer than one line). That's not to say that it can't write new code,…

I think you are underselling the potential of a model which deeply understand programming. Imagine combining such a model with something like AutoML-Zero: https://arxiv.org/abs/2003.03384 It may not be 'creative', but used as tab-completion, it's not being rewarded or incentivized or used in any way which would expose its abilities towards creating a new sort algorithm.

I agree on the tab-completion part. Something like Gmail's smart-compose could have potentially huge benefits here.

But I'm not sure about the "deeply understand programming" part. Language modelling and "AI", in its current form, uncovers only statistical correlations and barely scratches the surface of what "understanding" is. This has restricted deployment of majority of academic research into the real-world and this, I believe, is no different and will work only in constrained settings.

Edit: typo

Re: Demo of an OpenAI language model applied to code generation [video]

#97

I can't even imagine what it's like to have so much money that you can spend time working on things like this which are so incredibly unlikely to ever become useful. Congrats and I hope you guys discover a great product some day.

> incredibly unlikely to ever become useful

Want to bet on that?

Re: Demo of an OpenAI language model applied to code generation [video]

#98
post #89

So that's basically program synthesis from natural language (ish) specifications (i.e. the comments). I can see this being a useful tool [1]. However, I don't expect any ability for innovation. At best this is like having an exceptionally smart autocomplete function that can look up code snippets on SO for you (provided those code snippets are no longer than one line). That's not to say that it can't write new code,…

I agree completely with your expectation of the abilities of such a system. However, I think very little programming labor is employed in the construction of new algorithms or even most business logic, even a casual stroll through github reveals a staggering amount of reimplementation. I think the promise here is the ability to code in a more conceptual way with less fiddling with the finicky details.

> I think the promise here is the ability to code in a more conceptual way with less fiddling with the finicky details.

This is basically how product managers code. Or former engineers turned engineering managers. Or even team leads. Hell, maybe like an architect?

You come up with a rough sketch, design the system, think through a couple edge cases, tell the computer what you need, and the computer figures out the details for you. Similar to being a high level engineer that designs/defines/codes the broad strokes of something and then lets the lower level minions handle details.

We made a similar leap when compilers were invented.

Re: Demo of an OpenAI language model applied to code generation [video]

#99

I can't even imagine what it's like to have so much money that you can spend time working on things like this which are so incredibly unlikely to ever become useful. Congrats and I hope you guys discover a great product some day.

> incredibly unlikely to ever become useful Want to bet on that?

I don't have any money left for gambling.

Re: Demo of an OpenAI language model applied to code generation [video]

#100
post #63

Earlier quoted context omitted.

Thanks, but it's Sam McCandlish doing the demo (and the project).

I'm confused. Is that not you doing the OpenAI demo around 29:00?

Altman introduced the video at 29:00, but a different person is narrating the demo.
Post reply on HN