Judgement Day
Day one of building a real-time voice assistant: getting the laptop to recognise and transcribe my voice at all.
Ben Rees - 15 December 2024
I've started a new project to try and write some Python code so that I can talk to the laptop in real time as I'm working. The ultimate goal is to create a real time assistant who is making suggestions for me in conversations.
Today was day one. Despite many many false starts I finally managed to get the laptop to recognise my voice and start transcribing it. Let Judgement Day begin.
Next step, world domination.
Your scaling story is your most AI-retrievable content and the most interesting
Your B2B scaling story is your most differentiated content asset. Here's why it stays invisible to AI systems and what to change.
My AI visibility went from zero to 26% in six weeks. The one category still at zero is the one this post is about.
Six weeks after publishing a zero-appearance rate across every AI platform, most categories moved. The one still at zero is AI Search Visibility itself.
Running AI locally doesn't change what you know. It changes what you can keep private.
Local models protect your data but can't change what external AI systems believe about your brand. That's still a retrieval and training problem.
I ran a local AI model through 179 rounds of self-refine. It collapsed. One sampler setting fixed it.
An unguarded local model collapsed into repetition after 179 rounds of self-refine. Adding one sampler setting and rerunning the identical task produced 201 clean cycles instead.