Viewing profile — nicktikhonov

From what I've seen, it's really easy to get PersonaPlex stuck in a death spiral - talking to itself, stuttering and descending deeper and deeper into total nonsense. Useless for a…

Yep. Seems like caching more broadly is something worth exploring next if I were to do a pt2.

Yep. I've been learning Chinese for the past 3 months, so the name was a fold-in inspiration from my other hobby :)

Glad to hear! I built my blog on top of NextJS - it basically just renders .mdx files with contentlayer. One of the things I discovered is that you can easily vibe-code these expla…

You're probably right, at least at scale this could help

One thing you can get the LLM to do is to call a "skip turn" tool, which will basically trigger the system to wait without saying anything. Then all it will take is clever promptin…

I feel like you could get pretty far with a raspberry pi and microphone/speaker. I think the hard part is running a model that can detect a "Hey agent" on-device, so that it can ru…

This is fascinating, thanks for sharing! I wonder why amazon/google/apple didn't hop on the voice assistant/agent train in the last few years. All 3 have existing products with exi…

I'd say it was a collaboration. I had to hand-hold Claude quite a bit in the early stages, especially with architecture, and find the right services to get the outcome I wanted. Bu…

100% - I thought about that shortly after writing this up. One way to make this work is to have a tiny, lower latency model generate that first reply out of a set of options, then …

Gross

A friend built this, everything working in-browser: https://ttslab.dev/voice-agent

Very cool! starred and on my reading list. Would love to chat and share notes, if you'd like

If you're of that opinion, you'll enjoy the new stuff coming out from nvidia: https://research.nvidia.com/labs/adlr/personaplex/

I'm sure LiveKit or similar would be best to use in production. I'm sure these libraries handle a lot of edge cases, or at least let you configure things quite well out of the box.…

I was using Twilio, and as far as I'm aware they handle any echos that may arise. I'm actually not sure where in the telephony stack this is handled, but I didn't see any issues or…

I didn't try Soniox, but I made a note to check it out! I chose Flux because I was already using Deepgram for STT and just happened to discover it when I was doing research. It wou…

If you read the post, you'll see that I used Deepgram's Flux. It also does endpointing and is a higher-level abstraction than VAD.

I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no prec…

Hey HN! I wanted an always-on AI agent for email, calendar, and scheduled tasks - but I didn't want to run a codebase I couldn't fully understand. So I built one small enough to re…

I'd do this for friends, but at scale this is unfortunately customs fraud

I spent a day (~$100 in API credits) rebuilding the core orchestration loop of a real-time AI voice agent from scratch instead of using an all-in-one SDK. The hard part isn’t STT, …

might be possible to solve this with prompt configuration. e.g. you'd be able to explain to the llm all the weird naming conventions and unintuitive mappings