Skip to main content

AI Engineering

Evals for Voice Agents (Session Notes)
·1102 words·6 mins
Notes of a whirlwind intro to evals for voice agents by Kwindla and swyx
Coding Agents as Slot Machines
·94 words·1 min
Interacting with LLM coding tools is much like playing a slot machine.
Pipecat Cloud Latency for EU Users
·182 words·1 min
Pipecat Cloud is located in the US. Is its latency ok for voice agents for EU Users.
K/V Cache Quantization in Ollama
·207 words·1 min
How to reduce memory consumption of large context windows.
Deploying Voice Agents to Production
·410 words·2 mins
Notes on a session about deploying voice agents to production by kwindla
The Speedy Solopreneur
·149 words·1 min
On the importance of speed for solopreneurs.
An Overview of the Voice AI Landscape (Session Notes)
·744 words·4 mins
Notes on a session by kwindla about the voice AI landscape.
A note on the Hidden Complexities of WebSockets
·226 words·2 mins
Things to keep in mind when working with WebSockets
RTX 5090 for Local AI
·550 words·3 mins
A look at the NVIDIA RTX 5090 specs for local LLM inference.