Nick (nt)

I'm building an app for language nerds and polyglots. I'm using it to learn Mandarin Chinese - it's helping me distill the insights from dozens of research papers on learning into a single, highly effective routine. I'm opening up access to a handful of alpha testers who are learning Chinese, German or Russian. Reply/DM if you're interested.

• 115 replies
• 11 recasts
• 384 reactions

the trick to making voice agents fast is pipelining everything: first pipeline: audio packets -> speech to text -> turn-taking model second: LLM -> text to speech -> encoding -> output here's a render of my current latency. bear in mind, I'm running this locally from a wooden hut in the mountains in Turkey - it should be significantly faster once I host it!

• 62 replies
• 8 recasts
• 393 reactions

Here's a mental map 👇 except it's not a map of some idea in your mind, it's a map of your mind and how well it remembered something. i'm using this to predict individual patterns of forgetting during learning in order to optimise how fast I can learn Mandarin.

• 39 replies
• 11 recasts
• 334 reactions

my Mandarin tutor is awesome. every session, he introduces ~25-35 new words and phrases, which builds my active vocabulary by ~20 words. I add them to my learning system, entering them into practice and consolidation - all managed by an algorithm that models my memory and manages my practice sessions. within my system, I can see my progress against the 2000 most frequent words and phrases (accounting for 90% of all everyday speech!). as I learn each word over the next few days, the pale dot turns bright as the concepts get lodged deeper into my memory and active recall improves. every week I climb 1-2% towards Mandarin fluency - and I know this for sure because every single aspect of my practice is meticulously tracked, in a fully automated way where AI does all of the work. the end result is incredibly satisfying:

• 76 replies
• 14 recasts
• 291 reactions