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, with EU/US timezone overlap Willing to relocate: No Technologies: TypeScript, React, Next.js, Node.js, Electron, Tauri, React Native, PostgreSQL, LLM integrations, Tesseract.js/OCR, Web Workers/WebAssembly, FFmpeg, WebRTC, design systems, CI/CD Résumé/CV: https://izmailov.dev/cv Email: anton@izmailov.dev Salary expectation: USD $130,000+/year

Staff/Senior product engineer with 10+ years of experience building complex web and desktop products. TypeScript is my strongest language. I work across architecture and implementation, especially where rich client experiences, backend systems, and AI workflows meet.

Recent work includes production Electron apps for macOS and Windows; low-latency screen recording with FFmpeg and Web Workers; and a screen-activity recognition system that uses local Tesseract.js OCR as a pre-check, with vision and LLM models for verification. At TheGuarantors, I led the UI kit and helped replace one-person ownership with a frontend committee and a practical contribution path for product teams. I have also reduced a build-and-test pipeline from more than 20 minutes to about 3 minutes.

I am looking for full-time Staff/Senior full-stack, AI product, desktop, or technical leadership roles. I am most useful on products with hard technical constraints and meaningful product ownership. Open to contract-to-hire or longer contract work.

Location: Madrid, Spain Remote: Yes, with EU/US timezone overlap Willing to relocate: No Technologies: TypeScript, React, Next.js, Node.js, Electron, Tauri, React Native, PostgreSQL, LLM integrations, Tesseract.js/OCR, Web Workers/WebAssembly, FFmpeg, WebRTC, design systems, CI/CD Résumé/CV: https://izmailov.dev/cv Email: anton@izmailov.dev Salary expectation: USD $130,000+/year

Staff/Senior product engineer with 10+ years of experience building complex web and desktop products. TypeScript is my strongest language. I work across architecture and implementation, especially where rich client experiences, backend systems, and AI workflows meet.

Recent work includes production Electron apps for macOS and Windows; low-latency screen recording with FFmpeg and Web Workers; and a screen-activity recognition system that uses local Tesseract.js OCR as a pre-check, with vision and LLM models for verification. At TheGuarantors, I led the UI kit and helped replace one-person ownership with a frontend committee and a practical contribution path for product teams. I have also reduced a build-and-test pipeline from more than 20 minutes to about 3 minutes.

I am looking for full-time Staff/Senior full-stack, AI product, desktop, or technical leadership roles. I am most useful on products with hard technical constraints and meaningful product ownership. Open to contract-to-hire or longer contract work.

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