Maria Khalusova
@mariak.bsky.social
Always growing, she/her, RAG builder, LLM whisperer, tech generalist
Once again, I completely forgot that I have this account. Oops
September 24, 2025 at 1:43 PM
Once again, I completely forgot that I have this account. Oops
Things move fast in AI. Every week brings new models, new capabilities, or new ideas to chase. It’s exciting, but also easy to get swept up in the pace and forget to pause, to touch grass, to zoom out and see the bigger picture.
🧵
🧵
June 13, 2025 at 4:57 PM
Things move fast in AI. Every week brings new models, new capabilities, or new ideas to chase. It’s exciting, but also easy to get swept up in the pace and forget to pause, to touch grass, to zoom out and see the bigger picture.
🧵
🧵
Asking “What is the best chunk size for RAG?” without any additional context is like asking, “What’s the best thing to wear?” Wear where? What’s the weather like? What size are you? Are you going to a wedding or hiking a trail? There’s no single answer that works for every situation.
🧵
🧵
June 12, 2025 at 7:07 PM
Asking “What is the best chunk size for RAG?” without any additional context is like asking, “What’s the best thing to wear?” Wear where? What’s the weather like? What size are you? Are you going to a wedding or hiking a trail? There’s no single answer that works for every situation.
🧵
🧵
Do the thing that you will regret not doing when you're old.
June 9, 2025 at 12:32 PM
Do the thing that you will regret not doing when you're old.
I went to check what new courses deeplearning.ai has, and was pleasantly surprised to see that the short course Marc Sun, Younes Belkada, and I have built over a year ago is still featured as one of the Top Rated courses 😍
May 30, 2025 at 7:47 PM
I went to check what new courses deeplearning.ai has, and was pleasantly surprised to see that the short course Marc Sun, Younes Belkada, and I have built over a year ago is still featured as one of the Top Rated courses 😍
I'm taking this whole developer becoming a farmer dream way too far, am I?
May 20, 2025 at 7:49 PM
I'm taking this whole developer becoming a farmer dream way too far, am I?
If you've been prioritizing urgent work,
make sure to prioritize important work.
make sure to prioritize important work.
May 15, 2025 at 12:38 PM
If you've been prioritizing urgent work,
make sure to prioritize important work.
make sure to prioritize important work.
How anyone can like peanut butter is beyond me.
May 12, 2025 at 2:32 PM
How anyone can like peanut butter is beyond me.
Nothing starts a Wednesday morning quite like your dog getting sprayed by a skunk 🤢
May 7, 2025 at 12:02 PM
Nothing starts a Wednesday morning quite like your dog getting sprayed by a skunk 🤢
I have some epic plans for this summer and none of you’ll be able to guess what they are.
May 2, 2025 at 10:23 PM
I have some epic plans for this summer and none of you’ll be able to guess what they are.
I'm starting a series of blog posts on RAG beyond the basic set up. In the first part, we're setting the stage. Why naive RAG is not enough, and how a lot of the issues can be traced back to data processing choices.
Part 1: unstructured.io/blog/level-u...
Part 1: unstructured.io/blog/level-u...
Level Up Your GenAI Apps: RAG Beyond the Basics – Unstructured
Learn why naive implementations fall short—and how smarter data preprocessing lays the foundation for reliable, high-performance RAG.
unstructured.io
May 1, 2025 at 12:48 PM
I'm starting a series of blog posts on RAG beyond the basic set up. In the first part, we're setting the stage. Why naive RAG is not enough, and how a lot of the issues can be traced back to data processing choices.
Part 1: unstructured.io/blog/level-u...
Part 1: unstructured.io/blog/level-u...
What you're not changing, you're choosing.
This is a gentle reminder for the next time you're prioritizing a cool new shiny thing over building the foundation or addressing tech debt.
This is a gentle reminder for the next time you're prioritizing a cool new shiny thing over building the foundation or addressing tech debt.
April 30, 2025 at 12:59 PM
What you're not changing, you're choosing.
This is a gentle reminder for the next time you're prioritizing a cool new shiny thing over building the foundation or addressing tech debt.
This is a gentle reminder for the next time you're prioritizing a cool new shiny thing over building the foundation or addressing tech debt.
Word of the day seems to be "sycophantic".
Thanks AI community for increasing my vocabulary :)
Thanks AI community for increasing my vocabulary :)
April 29, 2025 at 2:20 PM
Word of the day seems to be "sycophantic".
Thanks AI community for increasing my vocabulary :)
Thanks AI community for increasing my vocabulary :)
32 pages - is it still a blog or do I call it a book now?
April 28, 2025 at 7:31 PM
32 pages - is it still a blog or do I call it a book now?
I don’t like the term “AI-assisted coding”. AI is just another tool in the box. We've had code completion and refactoring features in IDEs for a hot minute now, do we call it “IDE-assisted coding”? We just use these things to make our lives easier.
🧵
🧵
April 25, 2025 at 1:32 PM
I don’t like the term “AI-assisted coding”. AI is just another tool in the box. We've had code completion and refactoring features in IDEs for a hot minute now, do we call it “IDE-assisted coding”? We just use these things to make our lives easier.
🧵
🧵
Apropos of nothing, here's a tip.
Some embedding models are robust against typos, and others are sensitive to them. That's a whole rabbit hole on its own 🤓, but long story short - this will matter if your users are fat-fingering the queries.
Some embedding models are robust against typos, and others are sensitive to them. That's a whole rabbit hole on its own 🤓, but long story short - this will matter if your users are fat-fingering the queries.
April 24, 2025 at 7:12 PM
Apropos of nothing, here's a tip.
Some embedding models are robust against typos, and others are sensitive to them. That's a whole rabbit hole on its own 🤓, but long story short - this will matter if your users are fat-fingering the queries.
Some embedding models are robust against typos, and others are sensitive to them. That's a whole rabbit hole on its own 🤓, but long story short - this will matter if your users are fat-fingering the queries.
Today I learned that Postgres doesn't delete columns. Not from the catalog and not from data files. Deleted columns are only "soft deleted". But they still exist.
And now I wonder if this is why the logo is an elephant. As in, it never forgets.
And now I wonder if this is why the logo is an elephant. As in, it never forgets.
April 24, 2025 at 2:14 PM
Today I learned that Postgres doesn't delete columns. Not from the catalog and not from data files. Deleted columns are only "soft deleted". But they still exist.
And now I wonder if this is why the logo is an elephant. As in, it never forgets.
And now I wonder if this is why the logo is an elephant. As in, it never forgets.
I think I pissed off Live Demo gods at some point, they were not on my side today.
April 15, 2025 at 6:28 PM
I think I pissed off Live Demo gods at some point, they were not on my side today.
I may need to travel to the US soon, and this genuinely worries me.
I just attended a conference in the US. We had one speaker detained and two others turned away at the border.
There are great conferences and science in the US, but with the way things are right now, it’s too risky to attend.
April 14, 2025 at 12:01 PM
I may need to travel to the US soon, and this genuinely worries me.
I'm looking for incredible people to join my team! If you're excited about AI and know that great AI starts with great data - If you love building, learning, and helping others do the same - DM me. Let's talk.
And if this sounds like someone you know, feel free to RT!
And if this sounds like someone you know, feel free to RT!
April 11, 2025 at 3:39 PM
I'm looking for incredible people to join my team! If you're excited about AI and know that great AI starts with great data - If you love building, learning, and helping others do the same - DM me. Let's talk.
And if this sounds like someone you know, feel free to RT!
And if this sounds like someone you know, feel free to RT!
We use RAG to look up context for an LLM, next step should be looking up available MCP Servers and their tools. We need a middle layer between the LLM and servers, to look up available tools based on the request instead of having all of that info blow up the context window.
April 11, 2025 at 2:58 PM
We use RAG to look up context for an LLM, next step should be looking up available MCP Servers and their tools. We need a middle layer between the LLM and servers, to look up available tools based on the request instead of having all of that info blow up the context window.
April appears to be a good month for hitting milestones.
April 10, 2025 at 3:05 PM
April appears to be a good month for hitting milestones.
Years of breaking down complex concepts to a broad audience turn out to be rather useful in vibe coding.
April 3, 2025 at 12:06 PM
Years of breaking down complex concepts to a broad audience turn out to be rather useful in vibe coding.
Figuring out Jira automations is not something I had envisioned for myself, but here we are 🤣
April 2, 2025 at 3:22 PM
Figuring out Jira automations is not something I had envisioned for myself, but here we are 🤣