Fine-Tuning: More Complexity Than Clarity

Fine-tuning AI models may seem appealing for tailoring them to specific needs, but it often leads to challenges and confusion. While one might think that fine-tuning could incorporate unique company knowledge or documentation into a model, this approach can backfire. The pre-existing knowledge embedded in the model tends to overshadow the newly added information, resulting in increased hallucinations or inaccuracies when addressing specific questions. In fact, fine-tuning is more effective for optimization tasks, such as refining a model's ability to generate SQL queries through targeted examples, rather than for integrating new factual information.

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

The first episode of The Pragmatic Engineer Podcast is out. Expect similar episodes every other Wednesday. You can add the podcast in your favorite podcast player, and have future episodes downloaded automatically.

Listen now on Apple, Spotify, and YouTube.

Brought to you by:

• Codeium: Join the 700K+ developers using the IT-approved AI-powered code assistant.

• TLDR: Keep up with tech in 5 minutes

—

On the first episode of the Pragmatic Engineer Podcast, I am joined by Simon Willison.

Simon is one of the best-known software engineers experimenting with LLMs to boost his own productivity: he’s been doing this for more than three years, blogging about it in the open.

Simon is the creator of Datasette, an open-source tool for exploring and publishing data. He works full-time developing open-source tools for data journalism, centered on Datasette and SQLite. Previously, he was an engineering director at Eventbrite, joining through the acquisition of Lanyrd, a Y Combinator startup he co-founded in 2010. Simon is also a co-creator of the Django Web Framework. He has been blogging about web development since the early 2000s.

In today’s conversation, we dive deep into the realm of Gen AI and talk about the following:

• Simon’s initial experiments with LLMs and coding tools

• Why fine-tuning is generally a waste of time—and when it’s not

• RAG: an overview

• Interacting with GPTs voice mode

• Simon’s day-to-day LLM stack

• Common misconceptions about LLMs and ethical gray areas

• How Simon’s productivity has increased and his generally optimistic view on these tools

• Tips, tricks, and hacks for interacting with GenAI tools

• And more!

I hope you enjoy this episode.

—