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

Next-generation AI models

tabnine.com

Post reply on HN
Print view View original

121–130 of 139 posts

Re: Next-generation AI models

#121

Post by mdaniel »

lozenge wrote: post #71
mdaniel wrote: post #6

For my curiosity, https://www.tabnine.com/code/java/classes/com.google.gson.Js... says it was taken from https://github.com/Vedenin/useful-java-links/tree/master/hel... which Tabnine annotates as "license: other" (it's actually CC-BY-SA-4.0 https://github.com/Vedenin/useful-java-links/blob/1f4278c9ad... >) but (a) does Tabnine not know about CC licenses? (b) how is the downstream user (i.e. the person accepting said…

There's a standard GitHub uses for license files (which must be at the root of the repo) which fills in the "license" field on the right column of the repo. If the standard isn't met then the link just says "View license". I imagine TabNine is pulling the license from the GitHub API. https://docs.github.com/en/repositories/managing-your-reposi... https://github.com/Vedenin/useful-java-links When master branch is rena…

A fine reason for them to bork the useful-java-links case, I guess, but your argument falls over for the 3rd link: https://github.com/MovingBlocks/Terasology/blob/develop/LICE... and the sidebar widget correctly says "Apache-2.0 license"

Re: Next-generation AI models

#122

Post by fxtentacle »

skohan wrote: post #63
nlh wrote: post #55

I might be a super weird use case BUT believe it or not I use both Tabnine and Copilot and I kinda like the combo. Here's how it works: I use Copilot for its multi-line code generation. It's vastly superior. (Sorry Tabnine). Gotta give credit to Tabnine for kicking off this space -- they had a multi-year headstart on Copilot and it was pretty cool when it first launched, but it just doesn't come close to Copilot. Ope…

Call me old fashioned, but I use my brain for mutli-line code generation

Call me old fashioned, but when I need to create so much boilerplate that code generation starts to make sense, I usually just try to solve the problem in another more concise way.

Re: Next-generation AI models

#123

Post by BrandonJung »

claytonjy wrote: post #107
BrandonJung wrote: post #92

Earlier quoted context omitted.

no need to worry we love good feedback here at Tabnine ;-) Your observations are appreciated. In this case we are using general code and not a custom model but if you would like a custom model then I would wager you would get better variable names... maybe even "awesome". Our goal with our customers is to build models based on the best custom code and input from the best developers so that your new devs can learn fro…

When looking across a single companies codebase, how will you distinguish "best practices" from "we know this is bad but it works don't break it"? I have yet to work somewhere where the former is more than 5-10% of the code in production so I worry about this making it harder to raise the bar. I would find it a more compelling pitch to say tabnine will help me and my teammates follow more general best practices, thou…

A model is only as god as the code that it trains on and the people it learns from. In your example above we can build a custom model on "best practices" code and not the companies codebase. Our work here has focused on working with ISV's like AWS, GCP, etc as they will have best practices for their tech. We then pull that together for a team in a custom model.

Re: Next-generation AI models

#124

Post by chiefalchemist »

davewritescode wrote: post #105
chiefalchemist wrote: post #96

Earlier quoted context omitted.

You don't see how you just shot yourself in the foot, do you? If nothing else the HN mantra is not "That's how we've always done it."

The entire programmer ethos revolves around building deep understandings of the level abstraction you're working at and deep diving into the layers below when necessary or even just for fun! I've watched people use co-pilot but and I'm not 100% convinced it's a good thing but I'm open to it. The problem I've seen is that in some cases it generates some really bad code, code that could've been replaced by usage of a s…

I see it differently. The entire ethos should revolve around product that works. Product the meets a market need. Product that brings joy (not friction) into the world.

Any tool that can meet that ends should be considered.

Put another way, users don't care what anyone (i.e., in engineering) does or does not know. They're not going to wake up and say "I only want to use products that don't use Copilot." Nobody cares about any ethos, etc.

Re: Next-generation AI models

#125

Post by chiefalchemist »

skohan wrote: post #113
chiefalchemist wrote: post #96

Earlier quoted context omitted.

You don't see how you just shot yourself in the foot, do you? If nothing else the HN mantra is not "That's how we've always done it."

Well I don't think I've shot myself in the foot, it seems a lot of people agree with me. I'm not against the idea of ai coding tools on premise, but it did strike me as kind of funny to imagine someone using two such tools at the same time. I'm more of a minimalist, and would generally prefer to have lean tools which get out of my way. The idea that every keystroke involves a back-and fourth with a server, and that m…

Why? They clearly explained how it works for them. What's funny is you not being open to new ideas. That's a worse sign for us all than Copilot.

Re: Next-generation AI models

#126

Post by claytonjy »

BrandonJung wrote: post #123
claytonjy wrote: post #107

Earlier quoted context omitted.

When looking across a single companies codebase, how will you distinguish "best practices" from "we know this is bad but it works don't break it"? I have yet to work somewhere where the former is more than 5-10% of the code in production so I worry about this making it harder to raise the bar. I would find it a more compelling pitch to say tabnine will help me and my teammates follow more general best practices, thou…

A model is only as god as the code that it trains on and the people it learns from. In your example above we can build a custom model on "best practices" code and not the companies codebase. Our work here has focused on working with ISV's like AWS, GCP, etc as they will have best practices for their tech. We then pull that together for a team in a custom model.

Cool, that makes sense.

Do you models incorporate any sort of time-based weighting, where more recent code is weighted more heavily? Seems like that would also help this issue, as more recent code tends to be closer to what we hope future code looks like. But then how do you let best practices evolve over time?

Re: Next-generation AI models

#127

Post by skohan »

torginus wrote: post #116
skohan wrote: post #63

Earlier quoted context omitted.

Call me old fashioned, but I use my brain for mutli-line code generation

I feel Copilot indispensable - with the constant emergence of frameworks, languages I need to keep learning, it really shortens the time it takes to get productive in an unfamiliar environment.

It's existed for less than a year and you find it indispensable?

Re: Next-generation AI models

#128

Post by skohan »

fxtentacle wrote: post #122
skohan wrote: post #63

Earlier quoted context omitted.

Call me old fashioned, but I use my brain for mutli-line code generation

Call me old fashioned, but when I need to create so much boilerplate that code generation starts to make sense, I usually just try to solve the problem in another more concise way.

Yeah exactly - in software development the problem is rarely that there is too much typing to do.

Re: Next-generation AI models

#129

Post by alar44 »

fartcannon wrote: post #112
alar44 wrote: post #37

Earlier quoted context omitted.

No, I don't want to cobble together an office suite, email server, user auth, identity management, file sharing, meeting scheduling, and messaging system from scratch and then train users how to use this Frankenstein system and also support it. Because you know vendors never blame each other.

Listen to how you're talking about it. That's why the need to go. They're poison. They poison everything.

I'm talking about it like someone who has used alternatives and came to like it after many years. It allows me to manage 250 users comfortably with 1 admin in a decently high turnover environment and spend my time actually getting work done rather than fiddling with APIs and random connectors. I don't have to even think about it and it's worth every penny.

Re: Next-generation AI models

#130

Post by torginus »

skohan wrote: post #127
torginus wrote: post #116

Earlier quoted context omitted.

I feel Copilot indispensable - with the constant emergence of frameworks, languages I need to keep learning, it really shortens the time it takes to get productive in an unfamiliar environment.

It's existed for less than a year and you find it indispensable?

I don't see the contradiction - if someone who started programming in the pre-Internet days in a text editor, then switched to an IDE with autocomplete and searchable docs, would it be hyperbole for him to say that he finds these tools indispensable?
Post reply on HN