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

Replit's in-browser coding AI

replit.com

Post reply on HN
Print view View original

81–87 of 87 posts

Re: Replit's in-browser coding AI

#81

Post by conductr »

nerdponx wrote: post #27
eachro wrote: post #19

Earlier quoted context omitted.

That's very impressive. Hats off to them! I dont think this is too out of the ordinary either though. I'd guess they started off with a LLM from hugging face, set up some pipeline to ingest code from replit repos to finetune the LLM. The ML aspect of this is not terribly hard given that they probably dont need to train a LLM from scratch. Figuring out how store and serve from replit repos (or publicly available code…

8 weeks is impressive for something like that, and it goes to show just how powerful our off-the-shelf tools have become. I think it's also a bit scary, because 8 weeks is very little time for testing, tuning, and validation of something as opaque as a machine learning model. If it worked right the first time, that's great. But there is still a lot of inherent uncertainty in ML projects. Decision makers need to take…

It’s not life or death though. It’s just giving some useful boilerplate that you’ll have to touch to make useful. They can learn as they go.

Re: Replit's in-browser coding AI

#82

Post by ignite »

No free trial? Not interesting enough to pay for, if I have no idea how useful it is.

If you are doing something new, you need to let people see what it will do, before they will give you money.

Re: Replit's in-browser coding AI

#83

Post by selykg »

googlryas wrote: post #80
selykg wrote: post #58

Earlier quoted context omitted.

Can I ask why you're so defensive about it? I feel like, if there's ANYTHING we have learned in the past decade or two it's that people who defend a company tend to be doing so for the wrong reasons. See Sony or Microsoft, or Apple or Android, etc. Defending a company is just weird. I look at replit as a tool, run by people. The tool might be cool, but the CEO made a bad decision and now I judge the product on that C…

I'm just tired of seeing the same low effort comments on HN when a given topic comes up. Google => when will they cancel this? Meta => metaverse what a joke Etc...

I mean, I think it's relevant still. My time to move on from this particular instance might be different than someone else's, and there may be people out there that did not hear about that particular story. Personally, I feel everyone should have the opportunity to make their own decision on what I believe are poor actions made by a company.

We do it every day, whether we realize it or not. As a people we should support the companies that do good, and we should be aware of the companies doing bad. There's room for grey in there, it's not a one size fits all. But if you aren't aware of the bad then you aren't informed in your decision making.

If it bothers you, sorry. But I see it as a pro. I had a really bad experience with Remarkable, every time it comes up, I point out my experience so that others who might be making their own decision can use my experience in their decision making. When a company performs poorly. I guess by the metric you've provided above, this would be a low effort comment by your definition.

Re: Replit's in-browser coding AI

#84

Post by lgas »

WithinReason wrote: post #24
Liquid_Fire wrote: post #4

Earlier quoted context omitted.

One thing I noticed is it seems to have an "Explain code" feature, giving you a textual explanation of a block of code you select, which I'm not aware of GitHub having.

You can just use the prompt "The above code does the following explained in English" in a comment to prompt CoPilot to explain its code. You could probably also engineer a prompt to translate code between languages.

Have you tried "This ruby code does the same thing as the following python code" in a comment?

Re: Replit's in-browser coding AI

#85

Post by WithinReason »

lgas wrote: post #84
WithinReason wrote: post #24

Earlier quoted context omitted.

You can just use the prompt "The above code does the following explained in English" in a comment to prompt CoPilot to explain its code. You could probably also engineer a prompt to translate code between languages.

Have you tried "This ruby code does the same thing as the following python code" in a comment?

I actually did something similar and it worked IIRC. It was python to C or the reverse.

Re: Replit's in-browser coding AI

#86

Post by ksaj »

lgas wrote: post #84
WithinReason wrote: post #24

Earlier quoted context omitted.

You can just use the prompt "The above code does the following explained in English" in a comment to prompt CoPilot to explain its code. You could probably also engineer a prompt to translate code between languages.

Have you tried "This ruby code does the same thing as the following python code" in a comment?

I wish I thought of that when I had the co-pilot trial. If that works, I might have had a different opinion of my experience with it.

Re: Replit's in-browser coding AI

#87

Post by m00x »

mr_toad wrote: post #68
m00x wrote: post #56

Earlier quoted context omitted.

If you look at licensed code, then write new code, do you also bring in those licenses? It's been proved in court that AI does not infringe on copyright or licenses since it generates things from an understanding of the whole, instead of directly stealing, just like the human brain does.

> If you look at licensed code, then write new code, do you also bring in those licenses? If the “new” code is close enough to be considered a derived work then you will need a license.

Same for all programmers out there. Copilot will need to be careful, and like with everyone else, they'll learn.
Post reply on HN