drshrey

Interviewer | New York, NY | Full-time | Founding Engineers | https://getinterviewer.com

Interviewer automates first-round screening interviews with an AI voice agent. We're well-funded, deployed with multiple customers and are already hitting non-trivial scaling challenges.

We're looking for founding engineers who have strong intuitions on implementing strong reliability, low-latency systems as well as realtime observability systems to go along with it. ML experience is a plus but the focus is on full-stack software engineering right now.

We pay above market, have all the healthcare benefits you could want and are in-person at our office in lower Manhattan.

Send an email to [email protected] (me, the CTO) if you're interested!

Thanks so much! We're using 11 labs (https://elevenlabs.io/docs/api-reference/text-to-speech) under the hood, but can't speak too much into the exact configuration of the model we're using and the dynamics we're setting given a certain text. Hope that helps!

Let us know if you have any feedback on the experience!

Really appreciate the kind words and excited for others to have a similar experience!

Thanks Anton!

Got tired of having to find GitHub code line link every time I wanted to share code with someone. Wrote a vscode extension to spit out the GitHub line link: https://marketplace.visualstudio.com/items?itemName=colo-lab...

Oh crap, sorry it was down; got it back up and running. Try it out!

Hey, I'm one of the creators of HamPanda. Just released a new update today for an RPG-like leveling system. I'm probably working on achievements next or King of The Hill where the person who scores the most number of pandas in that hour gets some sweet bonuses.

Thanks, working on it!

Yeah, I'm going to make that clearer in the next update. It's much simpler, 'ON' means make the page translatable and 'OFF' means to leave the page alone. Because sometimes you just want to read the damn thing

Haven't seen this before but reading through discussions right now. This is really helpful, thanks.

If anyone's interested, the repo's right here: https://github.com/drshrey/alpharabius

OH! And it works on other sites too, but that's "experimental" since it's not tested on all sites (which is why we put the on/off slider). Might be interesting to build a DOM parser- in the future -that figures out where relevant, "could be translated" content is in the webpage.

Thanks for the support! But yeah, what lotyrin said. You should keep working on it because making a genuinely helpful language learning service isn't an easy problem by any means.

EDIT: And it needs all the help it can get.

Thanks, there's a LOT of room for growth and definitely not an easy problem to solve. More updates in the future, though!

Yeah, definitely not hard at all. Although, I think the harder problem is figuring out a specific word's complexity so it corresponds to the relevant immersion factor. For instance, having a lower immersion level shouldn't just mean lesser words (which is what is right now) but also more common and memorable words. Maybe a type of sentiment analysis problem?

Oh neat. Yeah, definitely going to check this out, and do an analysis on what these guys get right and features that might need to be improved on. Appreciate the links!