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

41–50 of 104 posts

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

#41

Post by aaomidi »

FpUser wrote: post #32
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…

>"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 can't argue with this in general as I do not have the statistics. Personally however I just never give CC info unless I tried the thing and found out that it does…

Well good thing is you don’t need to on Apple. Just get the free trial and cancel immediately?

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

#42

Post by jacob-jackson »

reaperman wrote: post #34
jacob-jackson wrote: post #15

Earlier quoted context omitted.

Sorry. We should be more clear about the CC being required to sign up for the free trial.

This goes against the guidelines for "Show HN". You can still post it, but generally it won't qualify for the Show HN moniker. You can review the rules for Show HN here: https://news.ycombinator.com/showhn.html > Please make it easy for users to try your thing out, ideally without barriers such as signups or emails. "Without signups or emails" definitely implies without credit card authorization!

I didn't realize that. I would have posted without the Show HN tag if I had read that carefully.

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

#43

Post by jacob-jackson »

anigbrowl wrote: post #37
jacob-jackson wrote: post #15

Earlier quoted context omitted.

Sorry. We should be more clear about the CC being required to sign up for the free trial.

How about just not having one? i am often interested to try things but I am not giving out my CC until I've tried it out, FOMO be damned. I don't want the burden of cancellation if I decide it's not for me, I've been burned before by forgetting and paying for a service I didn't want.

We think this is the most sustainable option because there is a cost to providing a quality service. We take a small loss on every user who cancels their free trial - more than a typical SaaS because AI models are expensive to serve.

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

#44

Post by twobitshifter »

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.

There’s a few options.

People think Gemini 1.5 is Sparse Mixture of Experts. (SMoE)

Another One is self extend. https://arxiv.org/abs/2401.01325

This paper also refers back to other options like yarn, etc.

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

#45

Post by cortesoft »

FpUser wrote: post #32
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…

>"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 can't argue with this in general as I do not have the statistics. Personally however I just never give CC info unless I tried the thing and found out that it does…

So do you just end up with a lot of unsolved problems? I get the principal, but does it end up hurting you in practice? Or do you end up solving the problem with a free tool? If so, I guess the product wasn’t really needed.

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

#46

Post by rglover »

huytersd wrote: post #39
avidphantasm wrote: post #19

If you don’t like writing code, find a different line of work.

It’s a matter of speed and delivery.

Speed and delivery of what, though? The religion of speed is blinding people to (what I thought was) the obvious trap of these tools: encouraging the incorporation of code the author likely doesn't understand into complex systems and just "trusting the robot is right."

For an experienced developer this may be about productivity, but 100M ARR at Copilot tells me we've got novices yeeting whatever code the LLM gives them into their work. So, you get two problems: systems with questionable integrity and a future generation of "engineers" who lack practical knowledge that can only be earned by solving problems.

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

#47

Post by _boffin_ »

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?

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

#48

Post by rrrix1 »

cortesoft wrote: post #45
FpUser wrote: post #32

Earlier quoted context omitted.

>"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 can't argue with this in general as I do not have the statistics. Personally however I just never give CC info unless I tried the thing and found out that it does…

So do you just end up with a lot of unsolved problems? I get the principal, but does it end up hurting you in practice? Or do you end up solving the problem with a free tool? If so, I guess the product wasn’t really needed.

Not OP, but some "problems" actually aren't.

More often, I'm looking for an easier / faster / better way to something I'm already doing, either because I want to do it _less_ (e.g. pay monthly bills) or I want to do it _more_ (e.g. find & read relevant news).

I'm Curious. Seeking innovation. Exploring.

Just because I can get water from a well with a bucket doesn't mean I wouldn't enjoy modern plumbing and irrigation.

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

#50

Post by rrrix1 »

jacob-jackson wrote: post #43
anigbrowl wrote: post #37

Earlier quoted context omitted.

How about just not having one? i am often interested to try things but I am not giving out my CC until I've tried it out, FOMO be damned. I don't want the burden of cancellation if I decide it's not for me, I've been burned before by forgetting and paying for a service I didn't want.

We think this is the most sustainable option because there is a cost to providing a quality service. We take a small loss on every user who cancels their free trial - more than a typical SaaS because AI models are expensive to serve.

Maybe a shorter trial would work?

Personally I only need about 30 minutes with a code autocompletion LLM to see if it will do what I want without pissing me off (and maybe even making me smile!)

Post reply on HN