izanton

Author here. I wanted to start a discussion about where the decision to take the floor should live.

I wrote this article about my attempt to use an external classifier to separate backchanneling and floor-taking intents, but it seems to have too much latency, so it becomes unusable both ways: using built-in VAD makes the experience choppy because any input interrupts the speech, and a custom one takes too much time before it processes the input and interrupt.

So how do you guys solve this problem in production? (Don't suggest waiting for the `gpt-live-x` family. Waiting is killing.

Location: Madrid, Spain.

Remote: Yes, EU/US timezone overlap

Willing to relocate: No

Technologies: TypeScript, Golang, React, Next.js, design systems/UI kits, accessibility, developer experience, Electron, Tauri, React Native, Node.js, Web Workers/WebAssembly, FFmpeg, WebRTC, PixiJS, TLDraw/Excalidraw-style canvas tools, Tesseract.js/OCR, Chrome extensions, CI/CD

Résumé/CV: https://izmailov.dev/cv

Email: [email protected]

Salary expectation: USD $130,000+/year.

=====

Senior+ frontend-leaning product engineer with 10+ years of experience. I’m passionate about complex user-facing products where UX, frontend architecture, performance, and business needs are a must!

I led the UI kit initiative that evolved from a DX tool into an important core layer for how the company plans and ships features. It was later integrated into the frontend committee to improve adoption and involvement and to drive frontend development at the company.

I also built various screen-recording tools using FFmpeg and Web Workers, and recently built a tool with Tesseract.js for OCR to quickly understand the screen and recognize patterns, then confirm them with more powerful OpenAI Vision for further processing.

I’m seeking new, complex challenges that require deep knowledge of the client-facing side of engineering, and I'm ready to join as a full-time senior+ frontend product engineer.

Location: Madrid, Spain

Remote: Yes, EU/US timezone overlap

Willing to relocate: No

Technologies: TypeScript, React, Next.js, design systems/UI kits, accessibility, developer experience, Electron, Tauri, React Native, Node.js, Web Workers/WebAssembly, FFmpeg, WebRTC, PixiJS, TLDraw/Excalidraw-style canvas tools, Tesseract.js/OCR, Chrome extensions, CI/CD

Résumé/CV: https://izmailov.dev/cv

Email: [email protected]

Salary expectation: USD $130,000+/year

=====

Senior+ frontend-leaning product engineer with 10+ years of experience. I’m passionate about complex user-facing products where UX, frontend architecture, performance, and business needs are a must!

I led the UI kit initiative that evolved from a DX tool into an important core layer for how the company plans and ships features. It was later integrated into the frontend committee to improve adoption and involvement and to drive frontend development at the company.

I also built various screen-recording tools using FFmpeg and Web Workers, and recently built a tool with Tesseract.js for OCR to quickly understand the screen and recognize patterns, then confirm them with more powerful OpenAI Vision for further processing.

I’m seeking new, complex challenges that require deep knowledge of the client-facing side of engineering, and I'm ready to join as a full-time senior+ frontend product engineer.

Oh wow, I didn't know Deno is still a thing, I thought it died in times of covid

I liked this guy at first, but his content is so boring, can predict it from the first second. Endless rant about how AI sucks, and I'm not sure but I feel like he uses AI to write these scripts himself.

I try to follow the motto of my university quantum physics professor: if you feel like quantum mechanics is making you more certain you understand it, you’re probably wrong and need to start over.

But as I understand it, the most "basic" approach now with qubit-based computers is to select the most popular answer across many runs and treat it as the "right" one.

I don't really understand how quantum chips work, but it's so interesting and cool (or it's not)

What if... we stop for a moment, and then, after thinking for a moment, we stop hammering nails with a microscope, and stop using token usage as a metric of productivity?

I know it's sounds stupid, but what if