GitHub Copilot • Hacker News Board

Re: GitHub Copilot

#951

Post by kyrra » Wed, Jun 30, 2021, 1:10 PM UTC

shishy wrote: post #247

as300 wrote: post #211

Earlier quoted context omitted.

Why would you say it's an error to use a float for currency? I would imagine it's better to use a float for calculations then round when you need to report a value rather than accumulate a bunch of rounding errors while doing computations.

micro-dollars are a better way of representing it (multiply by 10e6); store as bigint. See: https://stackoverflow.com/a/51238749

Googler, opinions are my own.

Over in payments, we use micros regularly, as documented here: https://developers.google.com/standard-payments/reference/gl...

GCP on there other hand has standardized on unit + nano. They use this for money and time. So unit would 1 second or 1 dollar, then the nano field allows more precision. You can see an example here with the unitPrice field: https://cloud.google.com/billing/v1/how-tos/catalog-api#gett...

Re: GitHub Copilot

#952

Post by sizt » Wed, Jun 30, 2021, 1:10 PM UTC

This is great. Programmers will be able to write bloated, non-intuitive, badly designed applications much faster now. Just what the world needs.

Re: GitHub Copilot

#953

Post by Jeff_Brown » Wed, Jun 30, 2021, 1:19 PM UTC

chimtim wrote: post #738

fzaninotto wrote: post #40

I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…

Unfortunately, one in 10 times is far from good enough (and this is with good prompt engineering which after using large language models for a while, one starts to do). I feel like the current generation of AI is bringing us close enough to something that works once in a while but requires constant human expertise ~50% of the time. The self-driving industry is in a similar situation of despair where millions have bee…

I keep wondering how much time it could possibly save you, given that you're obligated to read the code and make sure it makes sense. Given that, the testimonials here are very surprising to me.

Re: GitHub Copilot

#954

Post by JackFr » Wed, Jun 30, 2021, 1:22 PM UTC

itsoktocry wrote: post #366

anthropodie wrote: post #335

Earlier quoted context omitted.

Few days back, Sam Altman tweeted this "Prediction: AI will cause the price of work that can happen in front of a computer to decrease much faster than the price of work that happens in the physical world. This is the opposite of what most people (including me) expected, and will have strange effects" And I was like yeah I gotta start preparing for next decade.

> Prediction: AI will cause the price of work that can happen in front of a computer to decrease much faster than the price of work that happens in the physical world. I'm skeptical. The envelope of "programming" will continue to shift as things get more and more complex. Your mother-in-law is not going to install Copilot and start knocking out web apps. Tools like this allow programmers to become more productive, wh…

You don't know my mother-in-law.

Re: GitHub Copilot

#955

Post by Jeff_Brown » Wed, Jun 30, 2021, 1:25 PM UTC

fzaninotto wrote: post #301

softwaredoug wrote: post #288

Earlier quoted context omitted.

It seems to replace/shorten the loop of “Google for snippet that does X” copy, paste, tweak, no? Which of course is super cool for many tasks!

It's smarter than that. It suggests things that have never been written. It actually creates code based on the context, just like GPT-3 can create new text documents based on previous inputs. Edit: Check this screencast for instance: https://twitter.com/francoisz/status/1409908666166349831

Is the model similar to GPT-3? That seems extremely resource-intensive, particularly given how fast the suggestions appear.

Re: GitHub Copilot

#956

Post by rexreed » Wed, Jun 30, 2021, 1:26 PM UTC

Given Microsoft invested $1B for an exclusive license of OpenAI's GPT-3 I wouldn't be surprised to see GPT-3 everywhere in all of Microsoft's products and in their acquisitions. Maybe we'll see GPT-3 in LinkedIn as well. Maybe don't believe everything you see on that network in the future (or now).

Re: GitHub Copilot

#957

Post by jonesn11 » Wed, Jun 30, 2021, 1:45 PM UTC

This is an interesting business model. One problem I foresee though is that frameworks can get outdated in a few years, and that might affect the text generation abilities.

Re: GitHub Copilot

#958

Post by lawwantsin17 » Wed, Jun 30, 2021, 2:06 PM UTC

But can it make the programmer understand the code as auto-diarrheas it out?

Re: GitHub Copilot

#959

Post by Tyr42 » Wed, Jun 30, 2021, 2:34 PM UTC

mkl wrote: post #907

lostmsu wrote: post #859

Earlier quoted context omitted.

I am not surprised. Bash is notoriously unreadable.

There is no bash code in that script, it's POSIX find.

POSIX find is also terrible. I'm sorry but I go out of my way to avoid using it as it's always a pain.

Re: GitHub Copilot

#960

Post by handrous » Wed, Jun 30, 2021, 2:37 PM UTC

maficious wrote: post #905

handrous wrote: post #387

Earlier quoted context omitted.

Until it automatically knows when and how it's wrong, you'll still need a human to figure that out, and that human will need to actually know how to program, without the overgrown auto-complete. May or may not reduce the demand for programmers, though. We'll see.

But that's exactly what you are doing as a programmer who uses it. If you autocomplete using it and then fix the code, you are literally telling it what it got wrong.

I was responding to "It could start to replace us in 20 years." I think if it can do that, it'll basically be AGI and a lot of things will change in a hurry. I don't think that a tool that can do that is even all that similar to this tool.