Joris Baan

🚀 Curious how to design, build, deploy, and scale a modern AI chat app with full control over the language model? Check out my new 2-part blog series + code! Part 1: Build microservices locally towardsdatascience.com/designing-buil… Part 2: Deploy to Azure towardsdatascience.com/designing-buil… 🧵👇 1/4

⭐ WEEKLY ROUNDUP ⭐ This lineup of articles tackle the nuts and bolts of building AI apps and leveraging their potential for well-defined goals, while avoiding common pain points. 🖊️ by @onlyMarcelM, @jsbaan, @ChengzhiZhao, @carolinabento, @murtazaali_5253 + more towardsdatascience.com/building-succe…

How can you go about designing and building an AI chat app? @jsbaan invites all tinkerers to follow along part 1 of his hands-on guide, focusing on microservice architectures and local development. towardsdatascience.com/designing-buil…

💸I provide a complete breakdown of the cloud infrastructure our app uses and their monthly costs in part 2. 💻 Full codebase at github.com/jsbaan/ai-app-…. 🧵4/4

🌐 Part 2: Cloud deployment and scaling How to make our local application available to real users at scale? Learn about Azure, Kubernetes, Azure Container Apps, horizontal scaling, load balancers, HTTPS and DNS. Read here 👉 towardsdatascience.com/designing-buil… 🧵3/4

🚀 Curious how to design, build, deploy, and scale a modern AI chat app with full control over the language model? Check out my new 2-part blog series + code! Part 1: Build microservices locally towardsdatascience.com/designing-buil… Part 2: Deploy to Azure towardsdatascience.com/designing-buil… 🧵👇 1/4

@bonadossou Hey, thanks for your interest! The workshop is indeed archival, and we discourage double submissions as this increases the reviewing burden on the whole community, and most NLP conferences prohibit it nowadays. We do consider finding papers with ARR reviews attached.

@jsbaan Is the workshop arxival ? What the policy around a submission currently in review for another conference ?

👋 Interested in submitting your work on uncertainty in NLP to our workshop UncertaiNLP, co-located with #EACL2024 in Malta? We have extended the submission deadline to Friday the 22nd of December. For more information, check out the website uncertainlp.github.io!

@shehzaadzd Hey, definitely saw that, it's in the thread!

@jsbaan Hey @jsbaan you might find our work “A Diachronic Perspective on User Trust in AI under Uncertainty” interesting. We explore how miscalibrations affect user trust. We’ll present it as an oral on dec 9th- 9:15am.

Attending #EMNLP2023 and interested in uncertainty estimation, selective generation and calibration? There’s a lot of super interesting work being presented! It’s really cool to see growing attention! ⬇️ An incomplete list of papers that I'm looking forward to checking out: 🧵

There's probably a bunch more that I missed, please mention them here. Same for any mistakes I made. I apologise for being too lazy to provide urls, authors etc. If you're interested in uncertainty and want to chat, let me know!

Main Conference Day 3️⃣ Sunday 10th 9:00-10:30 (posters) - CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation - Uncertainty Guided Global Memory Improves Multi-Hop Question Answering

Some highlights on recent work from my group @AmsterdamNLP to be presented at #EMNLP2023 this week, with wonderful students and collaborators. Themes include language generation, computational psycholinguistics, multimodality and more! (I'm in Singapore if you want to chat) 🧵👇