[HN Gopher] Show HN: Supermaven, the first code completion tool ...
___________________________________________________________________
Show HN: Supermaven, the first code completion tool with 300k token
context
Author : jacob-jackson
Score : 18 points
Date : 2024-02-22 21:49 UTC (1 hours ago)
(HTM) web link (supermaven.com)
(TXT) w3m dump (supermaven.com)
| maxchehab wrote:
| I've been using Supermaven for the past week and it's obviously
| better than copilot. Excited to see this product evolve!
| edent wrote:
| Whose code is it trained on? Do you respect their software
| licences?
| CrimsonRain wrote:
| next you'll say I need a license to read your comment because
| I'm copying it in my mind. Crazy!
| i_am_proteus wrote:
| >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.
| Nevin1901 wrote:
| Interesting launch. I saw you were the original founder of
| tabnine. I'm curious as to what you've learned since you launched
| tabnine in 2018, and why you're deciding to create another code
| completion ide extension.
|
| Will be trying this out.
| jacob-jackson wrote:
| I had the idea for the technology first and decided that code
| completion was the application where it would be the most
| useful. It's a proven market with Copilot having over $100M
| ARR.
|
| There are lots of other potential use cases for the technology,
| but they involve more business risk (ie, the risk that you
| create a technically sound product that isn't very useful).
| pr337h4m wrote:
| Off topic, but do you have any plans for same.energy? No image
| search tool has surpassed it even after two years.
| vlovich123 wrote:
| Does this involve uploading the git project to Supermaven and
| code completions are done in the cloud or is all this running
| locally? Or is it hybrid where there's some cloud processing and
| inference happens locally?
___________________________________________________________________
(page generated 2024-02-22 23:00 UTC)