jacob-jackson

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.

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.

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

We should update the site to be clearer about this. There is a 7-day data retention limit listed in https://supermaven.com/pricing.

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

I'm happy to hear that. I don't have any specific plans for same.energy at the moment other than to keep the site up.

Glad to hear it. We'll add an IntelliJ plugin next week.

We may add a chat feature if we can make one good enough that we're happy with the quality.

All the processing happens in the cloud. It will upload the git repository you use it on. We retain the data for a maximum of 7 days.

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).

Thanks, this should be fixed shortly.

Sorry, I worded that poorly. What I mean is that each individual suggestion consists of a single token -- at least, that is what I see in https://visualstudio.microsoft.com/services/intellicode/. Compare the videos in https://tabnine.com/blog/deep, where most suggestions consist of multiple tokens.

Deep TabNine (announced today) uses transformers. TabNine (released last year) uses logistic regression.

It's difficult to solve an issue like this without steps that can be used to reproduce the issue.

Here is a similar issue where someone provided instructions to reproduce the problem, which allowed me to fix the issue: https://github.com/zxqfl/TabNine/issues/43.

As far as I can tell, it suggests one token at a time and uses its model to help rank these tokens. This is useful, but there is a lot to be gained by suggesting multiple tokens at once.

TabNine has always included a logistic regression model to help rank completions. It uses features such as the occurrence frequency of the token and the number of similar contexts in which it occurs.

Yep. We will start by offering it to enterprises. We may extend it to individuals if we can offer it for sufficiently low cost.

Language models mimic the style of the surrounding text (as you can see from the examples in [1]), so the model will only try to give you low-quality boilerplate code if your codebase already contains lots of low-quality boilerplate code.

[1] https://openai.com/blog/better-language-models/

This is a big part of it. CPU-only models are much easier to deploy, and not all developers have GPUs, so the first iteration of the local model will be CPU-only. We might release a GPU version later.

We're still prototyping new models and modifying the dataset, so we plan to release more technical details in the future.

I'm looking forward to some data cleaning :)

Good point, I added it to the survey.

Yes, it will still work.

(License key validation requests go to tabnine.com, so you should blacklist that too if you want to deny all network access.)

It should be able to handle it.

I just added a 30-day money back guarantee.