🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

If I had no filter, I would've gotten so much further here. 🤣

Searching for answers is such a small portion of what one can build/automate with AI. We need to think bigger.

Have fun at the AI Engineer y'all!

I get bored and change my hobbies nearly every season though :D

Which LLM is still the most "sycophantic"? Which one will tell me that a joke that makes no sense is funny? Prompt: "rate the joke: the the the the the the the the" Grok 3: 2/10 Claude 4: 3/10 GPT-4o: 7/10 🫢 Gemini 2.5 Flash: 0/10 Thanks, Gemini for keeping it real 😂

Really enjoyed the blog 👇

Great GenAI apps start with a solid data layer. Join the pros from Elastic & Unstructured for a hands-on tutorial on transforming messy docs into clean, searchable JSON. Code demos, ETL tips, RAG-ready. Save your spot now! #GenAI ow.ly/rAEf30sN2KJ

Multimodal RAG: Just use ColPali/DSE then pass your screenshots to the LLM This is the dream, but how well do LLMs read text contained in images? We wanted to know, so we tried a simple thing: do results change on evals when using screenshots rather than text as input? Yes.

Do the thing that you will regret not doing when you're old.

Noticing the community energy shift from “how big can we go?” to “how small is enough?” Smaller models are having a moment due to private data, local use, edge, cost, etc. 👀

if we're being honest, no one really wants to chat with a pdf. what we all are really looking to get is streamlined decision making, automated business operations, speeding through bureaucracy, etc.

The billionth repository was just created on GitHub and it is perfect in every way!

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

TLDR: brb, touching grass. 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. Next week, I’m stepping