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

71–80 of 139 posts

Re: Next-generation AI models

#71

Post by lozenge »

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 renamed to main, GitHub redirects any old links. https://github.com/github/renaming#renaming-existing-branche...

Re: Next-generation AI models

#73

Post by droid_w »

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…

No post body was provided.

Re: Next-generation AI models

#74

Post by bluelightning2k »

I feel for TabNine.

What they're doing is impactful, impressive - and so eclipsed by an unreasonably well-resourced competitor that they don't even get given much credit.

"Not as good as CoPilot" really doesn't say enough about something that's still very impressive.

Personally I thought it was cool but not game-changing, and moved on when I got into CoPilot. I can't comment on the next-gen models.

Re: Next-generation AI models

#75

Post by bluelightning2k »

jollybean wrote: post #68
nevster wrote: post #27

Earlier quoted context omitted.

Seconded. Tabnine's suggestions were way worse than IntelliJ's suggestions. It was very annoying. Uninstalled it after a giving it a good try.

I uninstalled T9 for this reason: bad suggestions superseding the regular autocomplete, this is just not good. I have yet to compare to copilot.

Same issue with the autocompletes pushing the ground-truth out.

I actually installed a third-party extension which implements their autocomplete differently.

So weird that they didn't hear such major/consistent feedback. (Maybe they didn't want to tank their 'suggestions taken' number?)

Re: Next-generation AI models

#76

Post by droid_w »

bluelightning2k wrote: post #74

I feel for TabNine. What they're doing is impactful, impressive - and so eclipsed by an unreasonably well-resourced competitor that they don't even get given much credit. "Not as good as CoPilot" really doesn't say enough about something that's still very impressive. Personally I thought it was cool but not game-changing, and moved on when I got into CoPilot. I can't comment on the next-gen models.

No post body was provided.

Re: Next-generation AI models

#77

Post by arcatek »

johnfn wrote: post #32
BrandonJung wrote: post #2

For this specific comparison, it’s essential to start from the technology, as many of the product differences stem from the differences in approach, architecture, and technology choices. Microsoft and OpenAI view AI for software development almost as just another use case for GPT-3, the behemoth language model. Code is text, so they took their language model, fine-tuned it on code, and called the gargantuan 12-billio…

The other commenters have pointed out that this is basically just PR, but even if we ignore that entirely, it doesn't make a lot of sense. A few issues I pulled out somewhat at random: > Copilot queries the model relatively infrequently Huh? It queries whenever you stop typing. > Copilot does not suggest code in the middle of the line, as its AI model is not best suited for this purpose This is at best false, at wors…

> Huh? It queries whenever you stop typing.

That's relatively infrequently - TabNine offered me accurate completion while still writing my code, whereas with Copilot I not only have to wait for it to return the answer, I also have to hope it knows an answer. If it doesn't, too bad, lost time for nothing.

Re: Next-generation AI models

#78

Post by saikan »

YotamShinan wrote: post #65
owlbynight wrote: post #18

I had to uninstall Tabnine because its resource usage was unacceptable. Hopefully they've addressed that, because it was using way too much of my CPU at times that it shouldn't have been.

Hi, Tabnine's DevRel here. I'm glad to say that we have addressed this issue: You can now easily opt-in to encrypted cloud mode through the Tabnine hub (find it under Public Model section). This option takes off most of the computing resources used to run Tabnine. That's just one out of many other improvements we've been working on lately, that are now generally available. I hope you'll give it another go! :)

Even after I enabled cloud model just today, the local binaries are still taking a lot of CPU resources in bursts of say once every four seconds, I have the latest versions of both the tabnine extension and vscode.
Post reply on HN