How Netflix Taught an LLM to Recommend Movies So That You Keep Watching
In this article, we will look at how GenRec was built.
15 min read
← All sources
ByteByteGo
Newsletter
Explain complex systems with simple terms, from the authors of the best-selling system design book series.
20 posts in the last 90 days · newest 7 Oct
Why LLMs Agree With You Even When You’re Wrong
When LLMs sometimes agree with incorrect claims, it is mostly because their training rewards such behaviour. This reward system is built on several things at once, such as accuracy, helpfulness, politeness, and responses that people like.
12 min read
The LLM Blindspot: Why Models Forget What’s in the Middle of Your Prompt
In this article, we’ll look at why LLMs have this bias against middle information.
11 min read
Last 3 days: AI Evals, October cohort
Secure your spot in AI Evals in Practice. Enrollment closes in just 3 days! If you’ve been thinking about joining, now’s the time.
EP228: How SSH Works
Secure shell is a method to access a remote machine securely over an unsecured network. It starts with a TCP connection from the SSH client to the remote machine (SSH server).
6 min read
Why State is the Hardest Thing in Software Design
In this article, we will look at why state is the hardest thing in software development and the multiple strategies that developers can use to manage it.
Paid
How DoorDash Built a Toolbox for AI Agents
In this article, we will look at how the DoorDash engineering team built this gateway and the decisions they made.
15 min read
Why Do LLMs Lie?
In this article, we will look at why this problem of hallucinations happens with LLMs and the techniques that can help make LLMs more dependable for answering.
12 min read
AI Agents Can Think. Now They Can Pay.
I attended a MPP event at Stripe HQ, where I spoke with Emily Sands and Matt Schulman from Stripe, along with Brendan Ryan from Tempo.
13 min read
EP227: Top 9 Places to Use Jev
Jev is TypeSafe AI’s first System One Model. It is 100x faster and cheaper than frontier LLMs.
5 min read
LAST CALL FOR ENROLLMENT: Rebuild YouTube with AI
Rebuild YouTube with AI, taught by a former YouTube engineer, kicks off on Saturday, September 26. Enrollment closes in 24 hours.
1 min read
The Life of Data: From Creation to Deletion
In this article, we are going to look at the entire data lifecycle from creation to deletion and the decisions that need to be taken at each step.
Paid
How to Customize a Model to Learn New Tricks
In this article, we are going to look at the various strategies to customize and fine-tune a model.
12 min read
How OpenAI Built GPT-Live
To understand how it all works end to end, we met with engineers on the GPT Voice team, Zahan Malkani and Justin Uberti (who created WebRTC).
14 min read
How to Run a Big Model on Cheap Hardware?
A large AI model can run on modest hardware only by reducing the memory it occupies, reducing the calculations it performs, or moving some work to slower hardware.
12 min read
EP226: API Concepts Every Software Engineer Should Know
Sending a request and reading JSON is one thing. Designing an API that other people can rely on is something where things get complicated.
6 min read
Migrations at Scale: Changing the Application Engine at 30,000 Feet
In this article, we will look at how migrations work at scale and the key strategies that can help make it as efficient as possible.
Paid
How LLMs Can Find a Needle in a Haystack
In this article, we are going to look at how LLMs can find a needle in a haystack.
12 min read
LAST CALL FOR ENROLLMENT: Build with Claude Code
We’re relaunching Build with Claude Code, a 2-day intensive cohort-based course taught by John Kim, who has trained hundreds of engineers at Meta to use Claude Code in real production workflows.
Do LLMs Have the Memory of a Goldfish?
In this article, we will learn how LLMs handle memory so that they are useful to end users in performing complex tasks that require conversation and holding context.
12 min read