Bytebytego @bytebytego

Weekly system design topics you can read in 10 mins. blog.bytebytego.com Joined March 2022

Tweets

2K
Followers

137K
Following

2
Likes

2K

Alex Xu @alexxubyte

4 days ago

Google Translate: The Ideas Behind Neural Translation A simplified illustration of common techniques. Not an exact map of Google Translate’s current system.

1 10 57 9K 58

View Details

Eve Bodnia @evelovesolive

6 days ago

EBRMs seem to be good for general combinatorics not just sudoku!

Alex Xu @alexxubyte

6 days ago

x.com/i/article/2082…

5 11 29 15K 40

1 7 32 4K 14

View Details

Alex Xu @alexxubyte

6 days ago

x.com/i/article/2082…

5 11 29 15K 40

View Details

Bytebytego @bytebytego

a week ago

How do you actually test your code nowadays?

Alex Xu @alexxubyte

a week ago

How to Test Your Code. Even When AI Writes It.

3 73 446 34K 522

0 1 16 5K 15

View Details

Alex Xu @alexxubyte

2 weeks ago

How SSH Works

15 185 1K 69K 959

View Details

Alex Xu @alexxubyte

3 weeks ago

x.com/i/article/2101…

5 15 75 16K 86

View Details

Alex Xu @alexxubyte

3 weeks ago

Top 6 Techniques to Make Your AI System Efficient Serving LLMs at scale is expensive. These 6 popular techniques reduce latency and cost, and make your system more efficient.

11 22 96 11K 95

View Details

Bytebytego @bytebytego

3 weeks ago

If you want to redo it yourself, here's the GitHub repo with step-by-step instructions you can follow: github.com/mikhailsychevb…

Watch an ex-YouTube engineer rebuild YouTube in 45 minutes. By the end it's running: - Home feed - Video upload to the cloud - Video playback from the cloud - Data in a real database - Search, using multimodal embeddings - Deployed to a real URL All of those explained in under

8 95 731 166K 1K

0 3 73 11K 83

View Details

Bytebytego @bytebytego

3 weeks ago

8 95 731 166K 1K

View Details

Alex Xu @alexxubyte

4 weeks ago

Jev is TypeSafe AI's first System One Model. It is 100x faster and cheaper than frontier LLMs. That opens up a lot of use cases people usually skip because the big models are too slow or too expensive for them. Here are 9 use cases where we think Jev could be used instead of an LLM.

53 337 2K 90K 2K

View Details

Justin Uberti @juberti

4 weeks ago

@zahanm and I sat down with the ByteByteGo team for a deep dive on the GPT-Live system. It's nicely illustrated and gets into a few details that we weren't able to cover in our previous GPT-Live blog post. Check it out!

Alex Xu @alexxubyte

4 weeks ago

x.com/i/article/2102…

14 50 507 83K 719

1 7 76 14K 97

View Details

Bytebytego @bytebytego

4 weeks ago

GPT-Live is the most natural, conversational voice model we've tried. Under the hood, it pairs a new generation of voice model architecture with a serving system built for low latency. To understand how it all works end to end, we sat down with two engineers on the GPT Voice team: Zahan Malkani and Justin Uberti (the creator of WebRTC). In our deep dive, you'll learn: - The three generations of voice systems: cascaded pipelines, turn-based end-to-end models, and full-duplex models - Why separating thinking from talking is the core idea behind GPT-Live - The engineering behind the serving system, including the live and async paths - How evaluation differs for full-duplex voice systems - Lessons for building realtime systems, and what's next for voice

Alex Xu @alexxubyte

4 weeks ago

x.com/i/article/2102…

14 50 507 83K 719

3 6 23 6K 20

View Details

Alex Xu @alexxubyte

4 weeks ago

LLM, RAG, AI Agent & Agentic AI

15 252 1K 57K 919

View Details

Alex Xu @alexxubyte

a month ago

🚀 Announcing ByteByteGo Live: learn AI live from real builders. I’ve spent the past 8 years on education: thousands of hours writing books, deep dive newsletters, YouTube, etc. Two issues I keep seeing are: 1) it’s very different to learn from real builders. 2) most online courses never get finished (~4% completion). Over the past 12 months, we’ve been working on what we can do to change that. Today, I’m excited to announce ByteByteGo Live: live cohort courses taught by real builders. - Taught by real builders. Our instructors include very senior engineers from Google, Meta, etc., as well as @KentBeck , the creator of TDD. They teach what they use in their own work. - Live cohorts. Every course runs live with a group of people, and instructors answer your questions in real time. The current lineup: - AI Engineering Fundamentals - Build with Claude Code - Build Production Grade AI Systems - Rebuild YouTube with AI - AI Evals in Practice - AI Cost Optimization - Trust-optimized AI Development We have big plans for the year ahead: more courses, more instructors, and deeper hands on projects. Check out go.bytebytego.com/live-launch-x and let us know what you think.

6 23 139 25K 190

View Details

Alex Xu @alexxubyte

2 months ago

9 Distributed Systems Patterns You Should Know

6 73 453 35K 376

View Details

Bytebytego @bytebytego

2 months ago

How the JVM Actually Works

3 148 824 192K 934

View Details

Alex Xu @alexxubyte

2 months ago

MCP vs RAG vs AI Agents

20 190 1K 57K 845

View Details

Alex Xu @alexxubyte

2 months ago

What keeps the Internet running. We probably forget they exist until the day something breaks.

5 56 276 15K 179

View Details

Alex Xu @alexxubyte

2 months ago

What Is Harness Engineering, Explained Visually.

25 180 1K 70K 1K

View Details

Alex Xu @alexxubyte

2 months ago

Visualizing a SQL query in 5 mins SQL statements are executed by the database system in several steps, including: - Parsing the SQL statement and checking its validity - Transforming the SQL into an internal representation, such as relational algebra - Optimizing the internal representation and creating an execution plan that utilizes index information - Executing the plan and returning the results