Earlier quoted context omitted.
I'm mostly curious how far the hockey stick will go up. Eventually most things level off.
To me the key issue are these 'hallucinations'--mistakes that seem plausible but are completely made up, like API endpoints that would be super useful except for the small problem that they don't exist. GPT4 is better than GPT3 on these but it still produces a lot of them. The question is whether these are somehow inherent to the LLM approach or whether scaling up and continued improvements can eventually get rid of…
GitHub Copilot X – Sign up for technical preview
601–610 of 771 posts
Re: GitHub Copilot X – Sign up for technical preview
#602Re: GitHub Copilot X – Sign up for technical preview
#603I would love to hear from other people here but I tried it for a while and dropped my subscription. For short things it was nice, but the larger the suggestion the worst it got. I found myself constantly mentally debugging the output it suggested, I do not know if it was faster but I was mentally exhausted by it, unable to go for long periods of time. Dumb code completion is predictable, I know I'll need to press dow…
- auto complete. This one is amazing but I’m not willing to spend 10/month for only that
- generate code inline. The main purpose of copilot. It works okay but too often I feel like I’m faster if I google things myself. Perhaps I’m just a very fast googler and reader. Wouldn’t surprise me
- use a solution and adapt it to my own code. I don’t know how this could work without copilot having access to my browser and knowing what I just read somewhere. I’m very excited about this but right now copilot does not seem the right tool
But above all I cancelled for two reasons: it’s too slow and I can’t trust my privacy and code IP to be respected
Edit: I also feel there is a lot of secondary information lost. If I google I have multiple tabs and windows and (temporal) structure. I also learn about neighboring concepts via stackoverflow comments, or I learn about how to navigate the docs for whatever I’m doing right now.
With copilot I am not exposed to all of this. Not yet
Re: GitHub Copilot X – Sign up for technical preview
#604Scary. For the first time in my life, I feel like my expertise is at risk of being rendered obsolete. Maybe not this year, but the writing is on the wall. Soon coding without an AI will feel as antiquated as delivering food by horse. And resistance is futile because markets will punish those who refuse. We'll probably need less and less developers as AI advance. Just like we need less manual labor in farms today. And…
At one time, people programmed without google or search engines. They literally used thick ass books, and had to read through them and then type out what they saw in the book. Today, that sounds absurd. Then came stack overflow and google. We search, pray we get a good result or someone else took the time to ask the question, then read (and sometimes copy+paste). Then AI assistants. I'm not exactly sure what's next,…
Even if it's absurd I still like to buy physical books. The information is better structured and I like holding a book and turning pages.
Re: GitHub Copilot X – Sign up for technical preview
#605It should be free, or at least significantly cheaper. It was trained on millions of person-days of work people shared for free. This is _our_ work being sold back to us. (ok, not really mine, I don't contribute to OSS very much; I should probably pay for it.. but you get my point).
Re: GitHub Copilot X – Sign up for technical preview
#606Earlier quoted context omitted.
Unfortunate about slack. It really seems to have stagnated. At least we have discord; I'm really glad they turned down Microsoft's 12 billion offer.
I think it's more about salesforce, I have a pretty negative opinion about them and everything they acquire seems to limp along or die (and the good employees leave immediately) - just seems like a boring place to be (nice sky scraper though). Microsoft has a better track record with acquisitions.
Re: GitHub Copilot X – Sign up for technical preview
#607Earlier quoted context omitted.
$50+ in monthly subscription fees? BRB buying some MSFT
If you want it cheaper: https://how2terminal.com This is when I build a product and then Microsoft releases it three weeks later -_-
$9 per month also makes it costly enough that I wouldn't buy it as a "just to have" kind of tool. I don't think I'd get $100 of value vs searching online, especially since I attribute some negative value to tools that can be taken away from me. I don't want to pay forever and be dependent on something that could disappear tomorrow.
I don't get why something like that needs to be an online service. I don't know much about AI, so maybe it's a lack of understanding on my part, but why can't I simply have a copy of the trained model on my local machine where there's no ongoing cost (to you) whenever I run a command? Isn't an online API a complex solution to a problem that could be solved with a local app + data?
Maybe I just lack understanding and the models are too big or the compute required to make a query is huge. If you could give some insight I'd genuinely appreciate it.
Even though I'd never buy it as a subscription, it's the kind of thing I'd pay for as a perpetual app. I'd wouldn't hesitate to pay $50 if I could install it on my machines and forget about it until it would be useful. I'd also expect to pay for updated versions of the models whenever I need them.
Regardless, I think it's amazing as a discovery tool. I don't mind reading 'man' pages to figure out details, but I always feel like it's a hassle to discover what command I need for certain tasks.
Also, I'm probably an outlier since I make a lot of effort to avoid tools that rely on an internet connection to function. IE: I won't rely on GitHub. I'll use it, but only as a push mirror.
Re: GitHub Copilot X – Sign up for technical preview
#608Earlier quoted context omitted.
- lock down of PC software to the Microsoft app store, probably roughly at the same time apple also tightens a lock down on macOS - more anti competitive steps to make installing desktop Linux on consumer hardware hard while arguing you could just use WSL and it's "for your security" and they are not anti Linux because they embrace Linux on servers - trying to kill Valve, there should only be Windows games and only t…
Do you honestly think that Microsoft is scared of Linux taking over the desktop?
It's about eliminating competition and especially preventing potential future competition, it's about maximizing control and power to the most you can without losing otherwise (due to e.g. law regulations lost consumer trust etc.). It's just a game of numbers and future prospect.
Just the fact alone that Valve has Linux as a form of "escape hatch" if Microsoft locks things down more. With a bit of "future potential" (Valve Gaming console which is more then "just" the Steam Deck) is enough for Microsoft to take actions like that from a purely calculative perspective.
And Linux Desktop _has_ future prospect, maybe not in context of how currently most Linux desktops are but prospect anyway.
I mean Linux desktop has a lot of additional challenges:
- like _massive_ fragmentation through every layer of components and users, often with a lot of more emotional then technical opinions
- much smaller financial resources etc. (the companies which invest are either small (e.g. System76) or are not focused on desktop Linux (e.g. Canonical, Red Hat, Valve))
- a lot of money is flowing into server Linux hence all decisions tend to be focused on the server aspect thing things which are negative for desktop Linux and can not be configured away. (Through also a lot of "accidental" improvements and maintenance.)
but even with all this challenges Desktop Linux is quite usable, actually for some people _more_ usable then Windows. The main problem is normally not missing functionality or hardware support but fragmentation. Fragmentation making it a bad deal to support Linux as a software vendor (getting better through Valve, Flatpack and Snap), fragmentation wasting dev resources, fragmentation making system management/hardware support harder, etc. As well as there not currently being too much monetary reason to invest into 1st party desktop Linux support (Valve is a special case, System76 is small).
But non of the reasons which make people not use Desktop Linux are fundamental, and under the right conditions _one specific_ Linux Desktop could become highly successful. It's very unlikely but it's still possible, hence there is reason to make sure it's not possible.
Re: GitHub Copilot X – Sign up for technical preview
#609Scary. For the first time in my life, I feel like my expertise is at risk of being rendered obsolete. Maybe not this year, but the writing is on the wall. Soon coding without an AI will feel as antiquated as delivering food by horse. And resistance is futile because markets will punish those who refuse. We'll probably need less and less developers as AI advance. Just like we need less manual labor in farms today. And…
Good. I'd rather not have to work forever. The whole point of this job is that I'm lazy. I don't want to do any work so I make machines do it for me. Why are people so attached to having to work?
Maybe this sounds naive to you, but if I'm not good for anything, what am I supposed to be doing? How should I see myself?
Re: GitHub Copilot X – Sign up for technical preview
#610Earlier quoted context omitted.
They’re strategically exceptional, but beyond that a lot of their products (or subsidiaries) are also dominant for good reason (vscode, GitHub). O365 and the product integration there (teams) is why they crushed slack despite slack’s headstart. Slack sold out to languish at salesforce while Microsoft will now just own that space. Cherry picking a Microsoft app for macOS is like looking at iTunes on windows, it’s not…
Slack sucks, but if you compare it with Teams, it is still gold. If anyone asks me, whether I wulould rather join a voice chat on Slack or Teams, the answer is 100% of the time Slack. You never know what bugs Teams will cook up this time to ruin your call. O365 is a child's toy for non-professional document creation. Quickly hacking a document together maybe. Any normal non-web office suite blows O365 out of the wate…