I thought it would be fun to test a variety of open source LLMs on actual client work using Codex cli. I created a benchmark test based on real client…
I was using Codex with DeepInfra-hosted models for my benchmarking test and ran into a small compatibility problem. Codex sends requests using OpenAI’s Responses API. DeepInfra provides an OpenAI-compatible API,…
I run Hermes on a separate computer instead of my daily machine. The remote machine can stay online all the time, keep scheduled jobs running, receive messages from Telegram or…