Alex Strick van Linschoten mlops.systems

Third time’s a charm: setting up instrumentation with Braintrust, Langfuse and litellm\. Braintrust ended up not being as ergonomic as Langfuse so I switch over midway\.

mlops.systems·49w

It’s important to instrument your AI applications\! I hope this can more or less be taken as given just as you’d expect a non-AI-infused app to capture logs\. When you’re...

mlops.systems·49w

I’ve been working on a project called [hinbox](https://github.com/strickvl/hinbox) - a flexible entity extraction system designed to help historians and researchers build...

mlops.systems·50w

Error analysis to find failure modes

mlops.systems·51w

How to think about evals

mlops.systems·52w

original ↗

mlops.systems·57w

original ↗

mlops.systems·61w

Building an MCP Server for Beeminder: Connecting AI Assistants to Personal Data

mlops.systems·64w

Tinbox: an LLM-based document translation tool

mlops.systems·65w

Starting the Hugging Face Agents course

mlops.systems·66w

AI Engineering Architecture and User Feedback

mlops.systems·66w

Notes on ‘AI Engineering’ chapter 9: Inference Optimisation

mlops.systems·66w

Dataset Engineering: The Art and Science of Data Preparation

mlops.systems·66w

Notes on ‘AI Engineering’ (Chip Huyen) chapter 7: Finetuning

mlops.systems·68w

Notes on ‘AI Engineering’ (Chip Huyen) chapter 6

mlops.systems·68w

Notes on ‘AI Engineering’ (Chip Huyen) chapter 4

mlops.systems·68w

Notes on ‘AI Engineering’ (Chip Huyen) chapter 3

mlops.systems·69w

Notes on ‘AI Engineering’ (Chip Huyen) chapter 1

mlops.systems·69w

Final notes on ‘Prompt Engineering for LLMs’

mlops.systems·69w

Assembling the Prompt: Notes on ‘Prompt Engineering for LLMs’ ch 6

mlops.systems·70w

Log in to enable infinite scrolling