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

Show HN: Supermaven, the first code completion tool with 300k token context

supermaven.com

Post reply on HN
Print view View original

81–90 of 104 posts

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#81

Post by edent »

leereeves wrote: post #79
tbrownaw wrote: post #53

Earlier quoted context omitted.

What exception?

Perhaps it's overly technical or even pedantic, but in light of arguments like "AI is just doing the same thing humans do", I think we should admit it: Yes, we are making a copy in our minds when we read something. I suspect such copies are allowed (as an exception to copyright law) mostly because lawyers and judges don't think about it. Nonetheless, once we do think about it, the law isn't required to treat humans a…

You are not making a copy - because you are not able to identically reproduce it.

And, if you are and you do, that's likely an infringement. Most jurisdictions say that, for example, you can't perform an in-copyright creative work without compensating the owner. Look at the lawsuit around George Harrison's "My Sweet Lord" for an example.

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#82

Post by oniony »

chenxi9649 wrote: post #33

Excited to see this on HN front page! Unlike others, I didn't mind the CC + 30 day trial. 30 days actually feels generously long as I don't see many other projects offering that. I think it's ultimately right move for this project to live long. After trying it for a bit on a very very large codebase(more than the context window supported, albeit I haven't done anything superr insightful yet), the code suggestion does…

Absolutely. I turned off Copilot at work for this reason: it disrupts my state of flow in a way that regular contextual suggestions do not.

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#85

Post by earthnail »

carstenhag wrote: post #76
earthnail wrote: post #26

Earlier quoted context omitted.

App developer here. Sadly, it’s what works. Put differently: when users browse for apps, it’s usually when their need for sth that solves the problem is relatively high. Which means you have a much higher chance of converting that user right now during onboarding than anytime later in the lifecycle of your app. I wish Apple properly displayed prices though instead of this sneaky vague “contains in-app purchases” text…

They do display prices of in-app-purchases last I know, somewhere in the app listing

Yes, but that price list is quite broken. A lot of apps have different price points - either for A/B testing, or because of discounts with partners, or educational discounts (we have a 50% discounts for students, for example).

Apple lists all prices in that list.

To make matters worse, if you ever decide to change your prices, you'll have both the old and the new prices in the list. Especially when you start out, you won't really know what a good price point is, and within a short amount of time the price list will be cluttered with all the prices you tried.

I'm sure Apple believes they're protecting the user here, but in reality they're serving neither the users or the developers with this.

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#86

Post by gardnr »

_boffin_ wrote: post #47
i_am_proteus wrote: post #4

>At Supermaven we've developed and trained from scratch a new neural network architecture which is more efficient than a Transformer (the current standard architecture) at integrating information across a long context window. Clearly something proprietary, but in between this and Gemini's claimed 10M tokens, assuming there's no RAG... I'm curious what might be happening behind the scenes.

Mamba?

definitely sounds like an ssm.

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#87

Post by solumunus »

jacob-jackson wrote: post #71
solumunus wrote: post #68

I signed up for the free trial and downloaded the extension. All I'm getting is a blank command prompt window "sm-agent.exe" that opens when I open VS code. So yeh, it's just not working for me at all. Tried opening VS Code as admin and no difference. Any suggestions?

Sorry to hear that. I'm not sure what's causing this. Could you share your Windows and VS Code version to help us reproduce the issue? sm-agent.exe is supposed to be started as a subprocess by the extension. It shouldn't be in its own window.

Windows 11, VS Code 1.86.2

At no point have I been asked to enter license details, is that supposed to happen when it initially runs?

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#88

Post by gardnr »

leereeves wrote: post #36
CrimsonRain wrote: post #6

Earlier quoted context omitted.

next you'll say I need a license to read your comment because I'm copying it in my mind. Crazy!

An LLM is not the same thing as a human mind and does not automatically receive the same exception to copyrights. Whatever you think makes sense, it would be wise to be careful, because the law might not turn out to be what you want it to be.

It will depend on the jurisdiction. It will be fun when a model is trained in Japan on material that would be copyrighted in the USA, then produces an image that is not able to be copyrighted in the USA.

> Japan's government recently reaffirmed that it will not enforce copyrights on data used in AI training.

https://cacm.acm.org/news/273479-japan-goes-all-in-copyright...

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#89

Post by thelastparadise »

p1necone wrote: post #40
aussieguy1234 wrote: post #27

>While a model like GPT-4 offers unmatched suggestion quality, it's impossible to run on every keystroke (unless you charge users $1,000/month) Still alot less than the average SWE salary and this cost will go down over time. Anyway, jokes aside, I usually don't use copilot tools in my IDEs. I have zero difficulty with coding itself. I would not enable one unless i'm trying to learn a new language or something. I can…

> I can see how they would be helpful for more junior level engineers I'd argue the opposite - give something like chatgpt/copilot to a junior engineer and they use it to generate a bunch of overly repetitive code that they don't understand . If they're trying to write anything even slightly non trivial it's not going to work. In order to get value from AI code generation you need to be competent enough to properly r…

> In order to get value from AI code generation you need to be competent enough to properly review the output.

And to know what to ask.

Re: Show HN: Supermaven, the first code completion tool with 300k token context

#90

Post by avidphantasm »

falleng0d wrote: post #75
mostlysimilar wrote: post #28

Earlier quoted context omitted.

I really must be missing something with all of these tools writing code for you. Shipping my entire codebase off to some unknown party does not seem like a worthwhile tradeoff for not having to write my own indentation function or whatever.

You are really missing it. It's more about preventing RSI by getting the boilerplate writing out of the way than having the tool do the actual work for you.

If you are writing boilerplate all the time, it’s time to introduce some abstractions and put them in a library.
Post reply on HN