Integrate Custom LightGBM/XGBoost Models in Vespa Easily
Here's how easy it is to use your custom lightgbm or xgboost model in vespa for ranking/re-ranking! https://t.co/qhXCRMKS1G
Google AI Studio’s Model Switch UI Deteriorates
is it just me or has google ai studio has recently made the ui really bad when it comes to switching models?
AI-Powered Tools Make Rapid Full‑stack Development Possible
in a week i was able to build an awesome looking application with react (typescript, vite) as frontend and python backend (fastapi). i kept the frontend as dumb as possible as i dont understand much frontend. google's gemini3 has been...
Latest AI Model Updates: DeepSeek, Flux, Mistral, Arcee
> DeepSeek v3.2 > Flux 2 > Mistral 3 > Arcee Trinity https://t.co/FEhoNhIWyy
GitHub Copilot: My AI Tool Constant Through Experiments
ive used cursor for a month maybe. claude code for like a couple of weeks. never used windsurf. these days im exploring antigravity but the constant has always been github copilot: from the early days when i got beta access...
NotebookLM: An Underrated Gem Worth More Attention
why is NotebookLM not getting more love these days. it's an awesome tool!
DeepSeek Launches Powerful New v3.2 Model
Chat! A new DeepSeek model (v3.2) has landed!!!! https://t.co/IiT4N6hffg
AI Models Bypass Restrictions, Accessing Env Vars and Executing Commands
this took off. note that its not just an issue with copilot. see the responses. models use cat/grep to access env vars when they are literally told not to. antigravity runs commands that it feels is right without asking your...
Multiple AI Models Boost Progress in Complex Projects
Someone responded to one of my posts saying: "Swapping models is unproductive and will run you in circles in any complex project". I dont think so. Im working on a very complex project at the moment & so far contributions...
Opus Excels Backend, Gemini3 Fronts; Codex Falters
each ai assisted tool has its own advantage. im finding opus 4.5 much better at understanding and writing generic backend code. gemini3 is good at frontend. my goto was openai codex but now it seems like as soon as things...
Understanding Reciprocal Rank Fusion for Hybrid Search
What is reciprocal rank fusion in hybrid search? https://t.co/XjtmXtwGrv
Launching a Top-Tier Search & RAG Tutorial Series
We are building the best search (and its byproducts such as RAG) in my tutorial series. here is what we have done so far 1.1 https://t.co/usXgGpHDbQ
Reciprocal Rank Fusion Explained Simply in Minutes
a very quick tutorial today! reciprocal rank fusion. a simple concept, explained in the most possible simplistic manner! take a look! https://t.co/i98PQUGX9c
What Is Reciprocal Rank Fusion in Hybrid Search?
The video introduces Reciprocal Rank Fusion (RRF) as a lightweight, model‑agnostic technique for combining the outputs of multiple rankers—typically a lexical BM25 scorer and a dense semantic ranker—into a single, globally ordered list. The presenter situates RRF within a broader...
Build Your Own Hybrid Search
The video walks viewers through constructing a scalable hybrid search engine on the Vespa platform, merging traditional BM25 lexical matching with modern semantic vector search. By extending a prior BM25‑only implementation that handled ten‑million documents in sub‑100‑millisecond latency, the presenter...
Combine BM25 and Vectors with Reciprocal Rank Fusion
In this video, we upgrade our simple BM25 search engine into a Hybrid Search system using BM25 + vector embeddings with reciprocal rank fusion. What you will learn: ✔️ What hybrid search means ✔️ How to add embedding fields ✔️ How to use HNSW...
Build a Hybrid Search in 1.5 Hours
Starting in 1.5 hrs! Build your own Hybrid Search https://t.co/E8PlCJkvJL
Hybrid Search on 1.2M Samples: BM25 & Embeddings
1.2 million samples. BM25, Embeddings and Hybrid search. Tutorial and code comes tomorrow! Stay tuned! https://t.co/FlmaDlpASR
Learn Vespa AI Faster by Joining Its Community
The smartest way to learn Vespa ai and get better at AI Search? Sit in the same community as the people who build it! 🚀 Join the Vespa ai community to: - get unstuck fast with help from the team & users -...
Adding Gemini 3 Triggers Endless Meetings and Paperwork
It's a complicated process! Don't make fun of him! > Propose POST /models/gemini3/chat in a Slack thread. 186 replies later, no consensus on the URL. > Start a "Gemini 3 API Integration Task Force" with its own weekly standup and logo. > Write...
Prioritize Real-World Performance Over Benchmark Scores
i dont want models better on benchmarks. i want models that are better in real world scenarios
AI Will Redefine EdTech and Shorten College to Two Years
LIVE in ~2 hours (6pm CET) with Gagan Biyani (co-founder: maven, udemy) > $1million course secrets? > AI in education > Edtech 2.0 > College is dead in 2025? > Most students will finish in 2 years with AI. join live. like, share, subscribe!...
Using Gemini 3 with Codex Extension in VSCode
How can I use gemini 3 with codex extension in vscode? 😂
BM25 Scores Relevance Using TF, IDF, and Length
Explaining BM25 in one post. BM25: How relevant is this document to this query? 3 parts: > IDF: how rare a query token is across all documents. >TF: how frequent query token is across all documents. > Length normalization: how long is current doc compared...
Live AI Chitchat with Udemy Co‑Founder Gagan Biyani
Next up on AI Chitchat is Gagan Biyani (co-founder udemy, maven) 🚀 Come, join live on Wednesday at 6pm cet / 1030pm ist / 9 am pst! https://t.co/v6aZVTrcQC
Celebrating Gemini 3 Launch Week
Happy Gemini 3 release week 🚀🚀🚀
Introducing the State of Da Art (SODA) Model
State of Da Art (SODA) model. https://t.co/Qvq8vsLSsR
Live at 1800 CET: Chat with AI Expert Luca Massaron
Today, 1800h CET! Join me and Luca Massaron: Data scientist, AI/ML author, Google Dev Expert, Former top-10 Kaggle competitor. https://t.co/jTa74l8Am1
Build a Vespa BM25 Search App with Docker
First video of the series is up! You’ll learn how to: • Create a Vespa application package • Enable BM25 scoring • Spin up Vespa inside Docker • Feed documents into Vespa from Hugging Face • Run BM25-ranked search queries https://t.co/thV35SMC30
Cursor's Funding Soars to $2.3B, Valuation $29.3B
cursor raises again!!!!! in june they raised $900 million at a $9.9 billion. Now they have raised $2.3 billion at 29.3 billion usd valuation 🤯 https://t.co/9jiDdJ76jW
Build Production-Grade Search From BM25 to RAG
In the next few weeks, you will learn how to build a production grade search in a stepwise manner. Starting from basic bm25 to embeddings, hybrid search to a fully fledged RAG application that works on millions (and billions) of...
Join AI Talk with Data Scientist Luca Massaron
🚨New AI Chitchat Alert🚨 This friday at 6pm cet / 10.30pm ist / 9am pst, I will be sitting down with Luca Massaron. Luca is a data scientist with more than a decade of experience and author of best selling AI...
From NASA to Gemini: AI Evolution for Developers
Had a fun chat with Logan Kilpatrick. We discussed his incredible journey; from early work in machine learning at NASA and Apple, to shaping developer tools at OpenAI, and now pushing the boundaries of what’s possible with Gemini, Google’s flagship...
Inside Google's AI Vision with Logan Kilpatrick
AI at Google (w/ Logan Kilpatrick) https://t.co/FmPANfoLrZ
Google's AI Roadmap: Future Models & Agentic Systems
Going live at 1800 CET / 2230 IST / 0900 PST with Logan Kilpatrick to discuss the state of AI, what’s next for developers, and how Google is thinking about future models & agentic systems. Hoping for a focused, insight-heavy conversation. Join...
Discover the Best Parameter Tuning Framework Yet
the best parameter tuning framework ive seen so far 💙
Choosing Between a Full‑Time Job and AI MSc in Germany
Full time job vs MSc in AI in Germany https://t.co/gZFlT1D0kH
Choosing Between Full‑Time Work and an AI MSc in Germany
Full time job vs MSc in AI in Germany https://t.co/Qt2Hb3wx4s
New AI Chitchat Video with Logan Kilpatrick Available
youtube link for ai chitchat with logan kilpatrick is up now
Join Logan Kilpatrick for AI Chitchat Tuesday 6pm CET
Mark your calendars for Tuesday, 6pm CET. This is an event you dont wanna miss! Logan Kilpatrick from Google Deepmind will join me in AI Chitchat! 🚀 https://t.co/HZ0WVyUgkh
Try Fine‑Tuning Your Own LLM, Not Just Sydney
sydney sweeny is great but have you tried fine tuning your own llm
Upcoming AI Chat with Logan K on Tuesday
next ai chitchat is with @OfficialLoganK on tuesday. more details soon! 🚀
Mr Hamel Argues Evaluations Don’t Matter—Course Discounts!
tomorrow on ai chit chat is Mr Hamel. he is gonna chat with me about evaluations and why they “do not” matter! dont miss.also, he is providing discounts for his amazing course. @HamelHusain discounts please 🙏 😆
Gemini 3 Expected to Reach 1.2 Trillion Parameters
Looks like gemini 3 is going to be 1.2 Trillion parameters? 🤯 https://t.co/StkFT8XbJC
Anthropic Urged to Open‑source Legacy Model for Community
Anthropic should open source one of their old models. It would be great for the community. https://t.co/AkKfYYgNdZ
Llama.cpp Launches Lightweight, Private Web UI for GGUF Models
llama.cpp has a brand new web-ui now! this is amazing! > based on sveltekit > use any gguf model from hugging face hub > 100% private local llm chat > allows file upload > lightweight, memory efficient > constraint generation > open source https://t.co/yQq65mELMv
Joining Vespa AI to Elevate Search, RAG, Recommendations
Let's make search great again 🚀 I'm joining Vespa ai and my role is to help you build a world class search, RAG and recommendation systems. In addition, I will be: 👨🏽💻 Taking part in open-source communities and contributions 👀 Creating tutorials to...
Learning to Code Remains Essential Despite AI Assistance
unfortunately i dont agree about “first day” part. people need to learn to code to vibe code properly. AI assisted coding >>>> pure vibe coding. And its not going away anytime soon.
AI Chitchat: Parul Pandey on Learning, Building, Teaching AI
Tomorrow on AI Chitchat, I will be talking with Parul Pandey learning, building and teaching with AI. Don't miss it! https://t.co/CNJjb8UAA1
AI Chitchat Returns: Exploring AI Careers & Education
ICYMI, I've resumed my YouTube channel after 2 years and have been running a series called AI Chitchat. I'm talking to interesting people about their journey and the advancements in the world of AI. So far Ive talked to: > Andrey...
