Recording Music

**Join Us for PyData Meetup @ Melio!** Get ready for insightful sessions, networking with the PyData community, and, of course, pizza and beer! A big thanks to **Melio** for hosting us and supporting the community. **📅 Details** Date: Sunday, June 14th, 2026 Time: 18:00 - 21:00 Location: Melio Office, Hagag Towers, North Tower, Floor 32, HaArba’a St 28, Tel Aviv Language: This meetup will be held in Hebrew **🕒 Agenda** 18:00: Gathering, snacks, and drinks 🍕🍻 18:30: Welcome words 18:45: **A Match Made in Heaven: LLM Judgment at Vector-Search Speed,** Shon Mendelson, Staff AI Scientist @ Intuit 19:15: **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb**, Dr. Adi Sarid, CEO @ Sarid Research 19:45: **Cost-Efficient AI Systems in Practice,** Michael Levinger, Senior AI Engineer @ Melio **🎤 Featured Sessions** **A Match Made in Heaven: LLM Judgment at Vector-Search Speed** **Speaker: Shon Mendelson, Staff AI Scientist @ Intuit** Last year, I spent far too long chasing a stubborn data quirk: why our system couldn't see that “The Law Offices of John Miller” and “Miller, John S. PLLC” were the same entity. It led to a bigger question: can you achieve LLM-level judgment at vector-search speeds? Traditional vector search is fast, but often misses subtle context like this, while relying entirely on LLMs is too slow and costly for production at scale. In this talk, I’ll share how we bridged that gap at Intuit with a hybrid system that combines fast vector search, efficient small transformer-based models, and fine-tuned SLMs. The result is a system capable of handling millions of weekly entity comparisons, significantly boosting recall while maintaining precision levels comparable to traditional methods. **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb** **Speaker: Dr. Adi Sarid, CEO @ Sarid Research** When GenAI dropped, our quant market research agency had a beautifully naive thought: "We can finally replace all our human labelers with a simple API call!" Spoiler alert: Scaling AI without hallucinations isn't quite that simple. Join us for a brutally honest, technical look at our data science team's journey from prompt-panic to AI-powered productivity. We’ll share our biggest wins and hardest lessons regarding evaluation frameworks, the rapid obsolescence of custom packages, and the newfound "full-stack audacity" of modern data scientists. **Cost-Efficient AI Systems in Practice** **Speaker: Michael Levinger, Senior AI Engineer @ Melio** Deploying large language models and AI agents in real-world systems requires a constant trade-off between cost, latency, and performance. This talk explores how to optimize LLM- and agent-based systems using techniques such as caching, model routing/cascades, tuning, RAG, and distillation—significantly reducing costs without sacrificing quality. Through a case study of an ATO-agent system, we’ll also cover practical approaches to cost estimation, monitoring, and budgeting. In addition, we’ll compare leading industry models—such as Gemini, Claude, and GPT—focusing on differences in response speed, cost efficiency, and real-world performance, and how to choose the right model for each use case within broader agentic workflows. **🚀 RSVP** Space is limited – RSVP now to secure your spot! We look forward to seeing you there! **📍 How to find us:** Enter the North Tower in Hagag Towers (Ha'Arbaa 28), go up to floor 32, and find us there. **We highly recommend using public transport, but if you’re coming by car, [here is a list of nearby parking lots](https://docs.google.com/spreadsheets/d/15GIvUZWui78k4b0EyikjvzNMnDede4lY/edit?gid=751370004#gid=751370004).**

**Join Us for PyData Meetup @ Melio!** Get ready for insightful sessions, networking with the PyData community, and, of course, pizza and beer! A big thanks to **Melio** for hosting us and supporting the community. **📅 Details** Date: Sunday, June 14th, 2026 Time: 18:00 - 21:00 Location: Melio Office, Hagag Towers, North Tower, Floor 32, HaArba’a St 28, Tel Aviv Language: This meetup will be held in Hebrew **🕒 Agenda** 18:00: Gathering, snacks, and drinks 🍕🍻 18:30: Welcome words 18:45: **A Match Made in Heaven: LLM Judgment at Vector-Search Speed,** Shon Mendelson, Staff AI Scientist @ Intuit 19:15: **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb**, Dr. Adi Sarid, CEO @ Sarid Research 19:45: **Cost-Efficient AI Systems in Practice,** Michael Levinger, Senior AI Engineer @ Melio **🎤 Featured Sessions** **A Match Made in Heaven: LLM Judgment at Vector-Search Speed** **Speaker: Shon Mendelson, Staff AI Scientist @ Intuit** Last year, I spent far too long chasing a stubborn data quirk: why our system couldn't see that “The Law Offices of John Miller” and “Miller, John S. PLLC” were the same entity. It led to a bigger question: can you achieve LLM-level judgment at vector-search speeds? Traditional vector search is fast, but often misses subtle context like this, while relying entirely on LLMs is too slow and costly for production at scale. In this talk, I’ll share how we bridged that gap at Intuit with a hybrid system that combines fast vector search, efficient small transformer-based models, and fine-tuned SLMs. The result is a system capable of handling millions of weekly entity comparisons, significantly boosting recall while maintaining precision levels comparable to traditional methods. **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb** **Speaker: Dr. Adi Sarid, CEO @ Sarid Research** When GenAI dropped, our quant market research agency had a beautifully naive thought: "We can finally replace all our human labelers with a simple API call!" Spoiler alert: Scaling AI without hallucinations isn't quite that simple. Join us for a brutally honest, technical look at our data science team's journey from prompt-panic to AI-powered productivity. We’ll share our biggest wins and hardest lessons regarding evaluation frameworks, the rapid obsolescence of custom packages, and the newfound "full-stack audacity" of modern data scientists. **Cost-Efficient AI Systems in Practice** **Speaker: Michael Levinger, Senior AI Engineer @ Melio** Deploying large language models and AI agents in real-world systems requires a constant trade-off between cost, latency, and performance. This talk explores how to optimize LLM- and agent-based systems using techniques such as caching, model routing/cascades, tuning, RAG, and distillation—significantly reducing costs without sacrificing quality. Through a case study of an ATO-agent system, we’ll also cover practical approaches to cost estimation, monitoring, and budgeting. In addition, we’ll compare leading industry models—such as Gemini, Claude, and GPT—focusing on differences in response speed, cost efficiency, and real-world performance, and how to choose the right model for each use case within broader agentic workflows. **🚀 RSVP** Space is limited – RSVP now to secure your spot! We look forward to seeing you there! **📍 How to find us:** Enter the North Tower in Hagag Towers (Ha'Arbaa 28), go up to floor 32, and find us there. **We highly recommend using public transport, but if you’re coming by car, [here is a list of nearby parking lots](https://docs.google.com/spreadsheets/d/15GIvUZWui78k4b0EyikjvzNMnDede4lY/edit?gid=751370004#gid=751370004).**

Come join our welcoming, low-pressure environment where you can practice performing, build confidence, stay motivated, and connect with others who play piano. Each session is intentionally structured and hosted to ensure everyone has time to play (if they choose), feel supported, socialize, and enjoy the experience. It’s not a class, but a thoughtfully guided space to help you stay consistent and make meaningful progress. **Details:** * Gatherings take place in a private home setting in the Northwest Columbus area (location to be shared after RSVPing) * Small group to keep the sessions personal and ensure everyone has time to play * Light snacks and refreshments provided Please ensure that you are able to accept chats and emails/messages via Meetup.com, as that is how I will provide the address and communicate with you closer to the event. You can message me anytime if you have any questions.

We'll meet at The Capital One Café, 167 Easton Town Center, Space A-103. This is in the main mall where the Microsoft store used to be, on your left if you're standing at the bottom of the AMC Theater escalator. Join us on Saturday for an hour of uninterrupted wordmaking! • What we'll do Join us for an hour of writing! We’ve discovered that it’s strikingly helpful to write with other writers. See if it’s true for you at 10AM on Saturday mornings. Be it a book, blog, script, essay, dissertation, resume, melody, poem or just plain work stuff, you are invited to write it with us. No one will see what you've written or give you unsolicited advice. Instead of just thinking about writing, come and get some real writing done. SCHEDULE: 10:00 - SESSION 1: quick intros. 10:10 - timer starts: write for 1 hour. 11:10 - chat / take off / keep writing. OPTIONAL SOCIALIZING happens at 11A-11:30ish. Writing is very solitary. Connecting (and sometimes even commiserating) with other writers is a cool thing. BEING LATE IS OKAY: just show up and get settled, then check-in with me after the session. (I’ll be the person with the Shut Up & Write! sign.) If you were on time, please be willing to make room for the friendly latecomer. Happy writing and I look forward to seeing you! • What to bring Whatever you need to be able to write! Bring earbuds/earplugs if you want to block noise or the occasional conversation by other patrons. Electrical outlets are limited, so charge your devices before whenever possible. See you at The Café on Saturday!

Let's mix and boogie! We'll start with social time over dinner/appetizers/drinks from 6:00-8:00pm. Then we'll get down with a live band [Shucking Bubba Deluxe](http://www.shuckingbubba.com/). COVER CHARGE: $10.00 (cash) SBD: A great danceable cover band playing popular genres of music - funk, classic rock, pop & club/dance. [Harry Buffalo](http://www.harrybuffalo.com/locations/westerville/) has a wide selection of quality appetizers and entrees. Harry Buffalo seating is first come/first serve this evening. We need a few folks to be there by 6:00pm or so to secure a table on the patio. DRESS: Late Summer Patio (picnic table friendly) BAD WEATHER CANCEL (usually by 4pm) PARKING: lots near restaurant and down the street. Do not park at Taco Bell.

The topic for June is "Roadtrip" Speak Easy: true stories, told live. The idea is simple: an audience, an open microphone, and great stories. Hilarious, gripping, poignant- it's up to you. Audiences are invited to come to listen or come to tell as folks from all corners of Columbus offer their stories live on stage! Held at Wild Goose Creative's warm, intimate space, this night of tales occurs on the 3rd Thursday of every month. Doors open at 6:30 pm, show starts at 7:00 pm. Please arrive early if you want to tell, as we generally only have room for a limited number of tellers, and the sign-up sheet has a tendency to fill up fast. Formed around the idea that people need stories--they're what hold and draw us together--SpeakEasy celebrates the strangeness and commonness of being human. And in a world of smartphones, Facebook, Twitter, and more . . . it gives people a real, breathing, in-person way to connect. The night is geared for true stories of all kinds, taking the best tales told around kitchen tables, in darkened pubs, on the street corner, and at late-night parties and giving them an audience. Speak Easy is also a great outlet for performers, writers, and artists looking to share their favorite stories and perfect their skills. We strongly encourage tellers to please tell the story rather than read it so we keep within the spirit of good storytelling and stay engaged with the audience. All are welcome. Hang around after the show for a drink and build community!