In this newsletter, we'll share industry news, interesting readings, useful libraries, and some pro tips for LLM development every week.

TLDR: What's in this week's issue of llmEngineer.weekly

  1. Paper:
  2. Useful Tool: Running models locally
  3. A Pro(mpting) Tip to get structured output from an LLM

Reading List

Industry Developments

Paper of the Week

32 methods for LLM Hallucination Mitigation

A recent paper has analyzed 32 different methods to reduce hallucinations in LLM outputs. These methods range from different prompt engineering techniques to prompt tuning and fine tuning.

Definitely a worthy read for developers working on improving LLM performance and reliability.

Practical Stuff

Have you tried this free tool?

LMStudio is one of my favorite tools for LLM development. It's a Desktop application that allows you to find and download models, and run them locally in a ChatGPT style GUI. You can even spin up a local server to hit the models via API request.