Maria Khalusova @mariak.bsky.social · 01/12/2025Just entered my next decade and I think it’ll be the best one yet. 120
Maria Khalusova @mariak.bsky.social · 24/09/2025Once again, I completely forgot that I have this account. Oops 010
Maria Khalusova @mariak.bsky.social · 13/06/2025PS: That said, I’ll probably still keep an eye on what’s happening and may even share some posts every now and then. I’ve got a lot of thoughts on RAG, data processing, LLMs/VLMs, etc., so I likely won’t disappear fully. 020
Maria Khalusova @mariak.bsky.social · 13/06/2025The work will still be here when I return. The AI won’t slow down, but also a couple of months won’t make a dent in the field. This moment, however, this chance to be fully present with my family? That’s something I don’t want to miss. 120
Maria Khalusova @mariak.bsky.social · 13/06/2025And even more grateful to work with a team that’s so supportive. Stepping away from work, especially in a field moving at warp speed, can feel counterintuitive. But for me, it’s a way to reconnect with what matters most. 120
Maria Khalusova @mariak.bsky.social · 13/06/2025Kids won’t be kids forever, and mine are getting ever so close to becoming teenagers. Now is time I know I’ll never get back. I’m incredibly grateful to be in a place, both professionally and personally, where this is possible. 120
Maria Khalusova @mariak.bsky.social · 13/06/2025Next week, I’m stepping away for a couple of months to take a sabbatical and spend time with my kids. I’m not burnt out. I’m following my own advice: do the thing you’ll regret not doing when you’re old. 140
Maria Khalusova @mariak.bsky.social · 13/06/2025Things 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. 🧵 120
Maria Khalusova @mariak.bsky.social · 12/06/2025RAG exists to solve different problems across varied domains. Understand the problem you’re solving and look at your data. 010
Maria Khalusova @mariak.bsky.social · 12/06/2025Once you have some answers to these, you can get further into the technical weeds and experiment with chunking to find an optimal size. Bottom line, however, is - there's no universal "best" chunk size. 100
Maria Khalusova @mariak.bsky.social · 12/06/2025* How much context do you typically need to retrieve to satisfy a typical query? Simple facts may only require a sentence or two. Creative tasks may require larger context. Analytical queries may need a whole bunch of supporting evidence. 100
Maria Khalusova @mariak.bsky.social · 12/06/2025They all vary in structure, style, and length. * What is your use case? Are you trying to answer questions with specific facts? Are you gathering multiple documents to summarize for a report? Do you pull from transcripts and need to preserve speaker attribution? 100
Maria Khalusova @mariak.bsky.social · 12/06/2025Same goes for chunking. The “best” chunk size depends on a range of factors, and without those, the question is incomplete. Here are some of the questions to ask instead: * What does your data look like? Financial statements, technical manuals, customer support transcripts are not the same. 100
Maria Khalusova @mariak.bsky.social · 12/06/2025Asking “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. 🧵 100
Maria Khalusova @mariak.bsky.social · 09/06/2025Do the thing that you will regret not doing when you're old. 020
Maria Khalusova @mariak.bsky.social · 30/05/2025I 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 😍 060
Maria Khalusova @mariak.bsky.social · 20/05/2025At least I have interrupted your doomscrolling with some cuteness! 020
Maria Khalusova @mariak.bsky.social · 20/05/2025I'm taking this whole developer becoming a farmer dream way too far, am I? 110
Maria Khalusova @mariak.bsky.social · 15/05/2025If you've been prioritizing urgent work, make sure to prioritize important work. 020
Maria Khalusova @mariak.bsky.social · 08/05/2025Part 2 is a high-level overview of advanced RAG techniques: unstructured.io/blog/level-u...unstructured.ioLevel Up Your GenAI Apps: Overview of Advanced RAG Techniques – UnstructuredExplore advanced RAG retrieval techniques—including re-ranking, hybrid search, metadata filtering, and Agentic RAG—that go beyond basic vector similarity to deliver more relevant, high-precision resul... 010
Maria Khalusova @mariak.bsky.social · 07/05/2025Nothing starts a Wednesday morning quite like your dog getting sprayed by a skunk 🤢 120
Maria Khalusova @mariak.bsky.social · 02/05/2025I have some epic plans for this summer and none of you’ll be able to guess what they are. 100
Maria Khalusova @mariak.bsky.social · 01/05/2025I'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...unstructured.ioLevel Up Your GenAI Apps: RAG Beyond the Basics – UnstructuredLearn why naive implementations fall short—and how smarter data preprocessing lays the foundation for reliable, high-performance RAG. 150
Maria Khalusova @mariak.bsky.social · 30/04/2025What 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. 010
Maria Khalusova @mariak.bsky.social · 29/04/2025Word of the day seems to be "sycophantic". Thanks AI community for increasing my vocabulary :) 000
Maria Khalusova @mariak.bsky.social · 28/04/202532 pages - is it still a blog or do I call it a book now? 030
Maria Khalusova @mariak.bsky.social · 25/04/2025you’re doing the work. You’re still making decisions, solving problems, and putting together something useful. Coding with AI only becomes “vibe coding” if you’re not paying attention or care to what you or your tools are doing. 100
Maria Khalusova @mariak.bsky.social · 25/04/2025good code. Are we now repeating the same sentiment but with LLMs? AI is just another tool - like a refactoring feature in the IDE or a debugger. Debugger doesn’t find the issue - you do, faster with its help. So does AI help you work faster or more efficiently, but at the end of the day, 100
Maria Khalusova @mariak.bsky.social · 25/04/2025Though there used to be people saying things along the lines of “You’re not a real programmer if you don't code without your IDE’s fancy features!" or "True devs only need Notepad and a terminal”. Surely, we’ve long moved past that. It doesn't matter what tools you are using - it's about writing 100
Maria Khalusova @mariak.bsky.social · 25/04/2025I 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. 🧵 120
Maria Khalusova @mariak.bsky.social · 24/04/2025E.g. `BAAI/bge-small-en-v1.5` vs `text-embedding-3-large` 020
Maria Khalusova @mariak.bsky.social · 24/04/2025Apropos 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. 110
Maria Khalusova @mariak.bsky.social · 24/04/2025Today 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. 161
Maria Khalusova @mariak.bsky.social · 15/04/2025I think I pissed off Live Demo gods at some point, they were not on my side today. 110
Maria Khalusova @mariak.bsky.social · 15/04/2025I don't really yet see a decline in the events hosted in the US. 100
Maria Khalusova @mariak.bsky.social · 14/04/2025I may need to travel to the US soon, and this genuinely worries me. 110
Maria Khalusova @mariak.bsky.social · 11/04/2025I'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! 111
Maria Khalusova @mariak.bsky.social · 11/04/2025We 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. 120
Maria Khalusova @mariak.bsky.social · 10/04/2025April appears to be a good month for hitting milestones. 040
Maria Khalusova @mariak.bsky.social · 03/04/2025Years of breaking down complex concepts to a broad audience turn out to be rather useful in vibe coding. 040
Maria Khalusova @mariak.bsky.social · 02/04/2025Figuring out Jira automations is not something I had envisioned for myself, but here we are 🤣 000
Maria Khalusova @mariak.bsky.social · 02/04/2025No, I only saw that one photo with that one slide taken by an attendee, haven't seen the entire deck shared. So as you say, there's a chance of this being a massive coincidence. 010
