Index

Write Stupid Evals

Evals should start simple and get progressively more complex. It's important to start simple because what we're aiming to do is to build a habit for writing these simple assertions early. By doing so, we can start taking our vibes and turning them into objective metrics. This allows us to compare different approaches easily and make a data-driven decision into what works and what doesn't.

Don't overthink it and really just use a assert statement at the start.

There's a famous story about a pottery teacher who divided their class into two groups. The first group would be graded solely on quantity - how many pieces they could produce. The second group would be graded on quality - they just needed to produce one perfect piece. When grading time came, something interesting happened: the best pieces all came from the quantity group. While the quality group got stuck theorizing about perfection, the quantity group learned through iterative practice.

Is RAG dead?

What is RAG?

RAG is a fancy way of stuffing additional information into the prompt of a language model. By giving the model more information, we can get more contextual responses that are contextually relevant to what we need. But don't language models already have access to all of the world's information?

Imagine you're starting a new job. Would you rather:

1. Have access to all of Wikipedia and hope the information you need is somewhere in there
2. Have your company's specific documentation, procedures, and guidelines

Synthetic Data is no Free Lunch

I spent some time playing with a new framework called Dria recently that uses LLMs to generate synthetic data. I couldn't get it to work but I did spend some time digging through their source code, and I thought I'd share some of my thoughts on the topic.

Over the past few weeks, I've generated a few million tokens of synthetic data for some projects. I'm still figuring out the best way to do it but I think it's definitely taught me that it's no free lunch. You do need to spend some time thinking about how to generate the data that you want.

The Premise

An example

When I first started generating synthetic data for question-answering systems, I thought it would be straightforward - all I had to do was to ask a language model to generate a few thousand questions that a user might ask.

You're probably not doing experiments right

I recently started working as a research engineer and it's been a significant mindset shift in how I approach my work. it's tricky to run experiments with LLMs efficiently and accurately and after months of trial and error, I've found that there are three key factors that make the biggest difference

1. Being clear about what you're varying
2. Investing time to build out some infrastructure
3. Doing some simple sensitivity analysis

Let's see how each of these can make a difference in your experimental workflow.

Why Instructor might be a better bet than Langchain

Introduction

If you're building LLM applications, a common question is which framework to use: Langchain, Instructor, or something else entirely. I've found that this decision really comes down to a few critical factors to choose the right one for your application. We'll do so in three parts

1. First we'll talk about testing and granular controls and why you should be thinking about it from the start
2. Then we'll explain why you should be evaluating a framework's ability to experiment quickly with different models and prompts and adopt new features quickly.
3. Finally, we'll consider why long term maintenance is also an important factor and why Instructor often provides a balanced solution, offering both simplicity and flexibility.

How does Instructor work?

For Python developers working with large language models (LLMs), instructor has become a popular tool for structured data extraction. While its capabilities may seem complex, the underlying mechanism is surprisingly straightforward. In this article, we'll walk through a high level overview of how the library works and how we support the OpenAI Client.

We'll start by looking at

1. Why should you care about Structured Extraction?
2. What is the high level flow
3. How does a request go from Pydantic Model to Validated Function Call?

By the end of this article, you'll have a good understand of how instructor helps you get validated outputs from your LLM calls and a better understanding of how you might be able to contribute to the library yourself.

Getting Started with Evals - a speedrun through Braintrust

For software engineers struggling with LLM application performance, simple evaluations are your secret weapon. Forget the complexity — we'll show you how to start testing your LLM in just 5 minutes using Braintrust. By the end of this article, you'll have a working example of a test harness that you can easily customise for your own use cases.

We'll be using a cleaned version of the GSM8k dataset that you can find here.

Here's what we'll cover:

1. Setting up Braintrust
2. Writing our first task to evaluate an LLM's response to the GSM8k with Instructor
3. Simple recipes that you'll need

How to create synthetic data that works

Synthetic data can accelerate AI development, but generating high-quality datasets remains challenging. In this article, I'll walk through a few experiments I've done with synthetic data generation and the takeaways I've learnt so that you can do the same.

We'll do by covering

1. Limitations of simple generation methods : Why simple generation methods produce homogeneous data
2. Entropy and why it matters : Techniques to increase diversity in synthetic datasets
3. Practical Implementations : Some simple examples of how to increase entropy and diversity to get better synthetic data

AI Engineering World Fair

What's new?

Last year, we saw a lot of interest in the use of LLMs for new use cases. This year, with more funding and interest in the space, we've finally started thinking about productionizing these models at scale and making sure that they're reliable, consistent and secure.

Let's start with a few definitions

• Agent : This is a LLM which is provided with a few tools it can call. The agentic part of this system comes from the ability to make decisions based on some input. This is similar to Harrison Chase's article here

• Evaluations : A set of metrics that we can look at to understand where our current system falls short. An example could be measuring precision and recall.

• Synthethic Data Generation: Data generated by a LLM which is meant to mimic real data

Grokking LLMs

I've spent the last year working with LLMs and writing a good amount of technical content on how to use them effectively, mostly with the help of structured parsing using a framework like Instructor. Most of what I know now is self-taught and this is the guide that I wish I had when starting out.

It should take about 10-15 minutes at most to read and I've added some resources along the way that are relevant to you. If you're looking for a higher level, i suggest skimming over the first two sections and then focusing more on the application/data side of things!

I hope that after reading this essay, you walk away with an enthusiasm that these models are going to change so much things that we know today. We have models with reasoning abilities and knowledge capacities that dwarf many humans today in tasks such as Mathetical Reasoning, QnA and more.