narenkmano

Does all your documentation live in figma as well? Or storybook?

Also, what does the evolution process (creating a new component or modifying an existing one) look like?

Thanks! Yeah, it's been a lot of fun hacking around with these models. I just checked out your open-source project; looks super interesting! It has a lot of things I've been wanting to implement. I particularly love the command completion and concept of a repository map.

The approach you've taken is the one I use the most in my workflow nowadays. I manually provide context to GPT4 and ask it to translate/fix issues in my code (at least provide high-level ideas about resolving issues). Pretty cool to see a CLI version of that.

Having the human in the loop has been crucial in practice. Your approach of having the LLM interact with your code base and collaboratively make edits is interesting.

Joining the discord; thanks for the invite!

You are right. We do send it to OpenAI, and it's mentioned in a couple of lines below. I meant to update the readme to mention it everywhere but forgot! I just pushed a fix.

This is still far better than uploading your codebase to a third-party service for indexing and embedding generation. This tool intends to solve that right now with OpenAI's function calling.

However, the dream goal is to eventually run an LLM locally on your machines and support search without talking to any third-party service - https://gpt4all.io/index.html. But they are yet to arrive; none of the open-source LLMs are even close to the level of performance or quality as GPT 4 yet.

No, doing everything by hand in the console, which has been super annoying. But don't want to spend time setting up terraform right now.

Congrats on the launch! I've had to deploy python/java services on AWS ECS services (for blue-green deploys) multiple times over the last six months and it's always been a pain to setup it up. Especially in a startup where I want to move as fast as possible it's been a pain to set up manually.

Is that something that is easy to setup with Argonaut?

Scrcpy was a tool that I used everyday during my android dev years!

Really cool to see audio integrated into scrcpy without having to use sndcpy - https://github.com/rom1v/sndcpy

We are not hiring at the moment. However, feel free to connect with me at [email protected]. I might be able to help with a referral, if you are interested.

Yes, we are using the android emulator. More info on how we do it here - https://www.wolfia.com/security. Eventually, i'll write up a detailed blog.

Good catch. Fixed!

We did consider the option of building our own servers but getting started with AWS is much easier because we don't have to maintain our own hardware, so we went with that. This allows us to move much faster and deliver features that users want instead of optimizing costs.

Good point. We have other options for sign up pretty high on our list. We wanted to launch the MVP as soon as possible to hear feedback so that we can talk to customers and iterate on the right thing. We'll prioritize this higher :)

We can look into it. Adding it to the backlog.

We're not running on AWS Lambda but we had the limit in place because our servers are pretty expensive to run. We are planning to add to the pricing model a pay as you go option which will allow for us to provide unlimited time per session.

Looked at the website. Looks pretty cool. Will check it out!

Thanks for the feedback, and let us know if your team is interested.

For the deployment, wolfia allows you to share builds before they are merged and solicit feedback from your team earlier. If you think about it, the feedback loop is much faster in practice than waiting for deployment and then getting the feedback. However, I do agree that the build step is a pain! Our vision is to bring the same experience web developers have to mobile essentially, so we'll take a stab at it in the future :)

Thank you! You should be able to try it out now. If you can't still, pm me at [email protected]

You can check out our security practices here - https://www.wolfia.com/security

Agreed with building credibility. We'll add our names and backgrounds along with the YC backing on our website soon.

Also, we plan to support an on-premises option in the future.

Yes, we plan to support different devices and API levels soon.

It isn't enabled by default. But, if you click on the keyboard icon on the control bar to the left of the emulator, you should be able to use your keyboard. This is something we plan to improve.

Those are some great use cases! We already support the sharing sessions with multiple users. You can tap on the copy link to share control button on the bottom right of the emulator page and send it to someone to share your session :)

Thank you! That's the next item on our roadmap. We plan to create a public API and gradle plugin to automate link creation.

Our vision is to have a stable link for your app that links to the latest version of the app so that people can quickly find and interact with it.

Great question. We don't support audio (including TalkBack) at the moment. But it's very high on our roadmap.

For iOS, we plan to support similar features and we will explore if we can use the Accessibility Inspector tool to support VoiceOver.

Yes, absolutely. It's on our roadmap.