After reading a nice post via HN about On Stepping Back, I habitually scrolled through the comments and found this nugget by evrimoztamur: Interacting with LLM coding tools is much like playing...

Pipecat Cloud is the easiest way to run a Pipecat driven voice agent in production. I’ve heard in the Voice Agents course that Daily.co, the company behind Pipecat Cloud, currently only has region...

A somewhat hidden feature of Ollama is K/V Cache quantization. K/V Cache quantization in Ollama is not on by default, so you need to activate it by setting the OLLAMA_KV_CACHE_TYPE environment vari...

These are my notes on the session about deploying voice agents to production of the Voice Agents Course. TLDR: Use a voice AI provider for simple, scalable deployment for production. Use a s...

In The Batch 300, Andrew Ng shared some insights on the importance of speed for startups and how to be fast as a startup: focus on one concrete idea (don’t hedge) quickly switch to a differen...

I’m so happy to be part of the Voice Agents Course by Kwindla and swyx. Yesterday, Kwindla kicked it off with an overview of the voice AI landscape. The pace, insights, and questions from the audie...

This is a quick guide on how to install Docker and Docker Compose on Raspberry PI. I use this on various Raspberry Pis 4 with 4 and 8 GB RAM, it’s tested with Raspberry Pi OS 64-bit 12 (“bookworm”)...

AI Apps are often expected to be realtime. On the web, realtime can best be implemented with WebSockets. Atul Jalan from Compose has written a nice blog post about The Hidden Complexity of Scalin...

Update (January 14, 2025): The RTX 5090 was officially announced at CES and will be available January 30, 2025. This post was updated with the aktual RTX 5090 specs. I kept the rumored specs in the...

The new ChatGPT Search feature, which is meant to “get fast, timely answers with links to relevant web sources” apparently can use information from internal sites, too. A first hint was given by S...