Subscribe
Sign in
Home
Notes
LLM Engineer's Handbook
Free Courses
Perks
Archive
About
Latest
Top
Discussions
From noisy docs to fine-tuning datasets
Generate instruct datasets for fine-tuning LLMs using distillation techniques
Feb 20
•
Paul Iusztin
17
Share this post
Decoding ML
From noisy docs to fine-tuning datasets
Copy link
Facebook
Email
Notes
More
Multi-modal embeddings in recsys: Beyond text and images
Fine-tune any LLM in four simple steps. Hidden bottlenecks in your code? Not anymore.
Feb 15
•
Paul Iusztin
13
Share this post
Decoding ML
Multi-modal embeddings in recsys: Beyond text and images
Copy link
Facebook
Email
Notes
More
Data pipelines for AI assistants
The backbone of successful AI systems
Feb 13
•
Paul Iusztin
24
Share this post
Decoding ML
Data pipelines for AI assistants
Copy link
Facebook
Email
Notes
More
2
Let's build a speech-to-speech chatbot
Apply speech-to-text (STT), LLMs and text-to-speech (TTS) to replicate ChatGPT's voice assistant feature.
Feb 11
•
Juan Ovalle
18
Share this post
Decoding ML
Let's build a speech-to-speech chatbot
Copy link
Facebook
Email
Notes
More
3
The tech stack for real-time recommendation systems
The hidden complexity of AI integration: A personal perspective. The future of database querying: Tabular semantic search.
Feb 8
•
Paul Iusztin
12
Share this post
Decoding ML
The tech stack for real-time recommendation systems
Copy link
Facebook
Email
Notes
More
Build your Second Brain AI assistant
Using agents, RAG, LLMOps and LLM systems
Feb 6
•
Paul Iusztin
215
Share this post
Decoding ML
Build your Second Brain AI assistant
Copy link
Facebook
Email
Notes
More
15
Lambda architecture’s comeback for AI systems
How to become a top 1% AI/ML Engineer. The evolution of RAG, semantic search, and retrieval systems
Feb 1
•
Paul Iusztin
38
Share this post
Decoding ML
Lambda architecture’s comeback for AI systems
Copy link
Facebook
Email
Notes
More
2
January 2025
AI off-the-shelf tools can't keep up
The most complex step in AI/ML in production? Why text-to-SQL is NOT the future of tabular data search
Jan 25
•
Paul Iusztin
15
Share this post
Decoding ML
AI off-the-shelf tools can't keep up
Copy link
Facebook
Email
Notes
More
6
Monolith vs micro: The $1M ML design decision
The weight of your ML serving architectural choice
Jan 23
•
Paul Iusztin
28
Share this post
Decoding ML
Monolith vs micro: The $1M ML design decision
Copy link
Facebook
Email
Notes
More
5
AI aggregation engine behind Square & Coinbase
My 2025 prediction on RAG, semantic search, and retrieval systems
Jan 18
•
Paul Iusztin
15
Share this post
Decoding ML
AI aggregation engine behind Square & Coinbase
Copy link
Facebook
Email
Notes
More
Stop using text-to-SQL for search. Here's why.
Multi-attribute vectors + natural language are changing how we find products online
Jan 16
•
Paul Iusztin
26
Share this post
Decoding ML
Stop using text-to-SQL for search. Here's why.
Copy link
Facebook
Email
Notes
More
Here’s a massive milestone to note for 2025
I’m beyond grateful for your support, feedback, and kind words.
Jan 12
•
Paul Iusztin
10
Share this post
Decoding ML
Here’s a massive milestone to note for 2025
Copy link
Facebook
Email
Notes
More
2
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts