How to Maximize LLM Performance (Lessons from OpenAI DevDay)

People often think that fine-tuning is what the should be aiming for. Funnest part from the talk was the story of fine tuning GPT-3.5 on the company slack so it &quot;learned their tone of voice&quot;.<p>The result:<p>&gt; Human: Write a 500 word blog post on prompt engineering &gt; AI: Sure I shall work on that in the morning&quot; &gt; Human: &quot;Do it now &gt; AI: &quot;ok&quot;