Articles for category: AI Tools

March 9, 2025

ikayaniaamirshahzad@gmail.com

Hyperparameter Optimization For LLMs: Advanced Strategies

Finding an optimal set of hyperparameters is essential for efficient and effective training of Large Language Models (LLMs). The key LLM hyperparameters influence the model size, learning rate, learning behavior, and token generation process. Due to their computational demands, traditional methods for optimizing hyperparameters, such as grid search, are impractical for LLMs. Advanced hyperparameter optimization strategies, like population-based training, Bayesian optimization, and adaptive LoRA, promise to balance computational effort and outcome. The rise of large language models (LLMs) is bringing advances in text generation and contextual understanding. Hyperparameters control the size of LLMs, their training process, and how they generate

March 9, 2025

ikayaniaamirshahzad@gmail.com

Announcing Automatic Liquid Clustering | Databricks Blog

We’re excited to announce the Public Preview of Automatic Liquid Clustering, powered by Predictive Optimization. This feature automatically applies and updates Liquid Clustering columns on Unity Catalog managed tables, improving query performance and reducing costs. Automatic Liquid Clustering simplifies data management by eliminating the need for manual tuning. Previously, data teams had to manually design the specific data layout for each of their tables. Now, Predictive Optimization harnesses the power of Unity Catalog to monitor and analyze your data and query patterns. To enable Automatic Liquid Clustering, configure your UC managed unpartitioned or Liquid tables by setting the parameter CLUSTER BY

March 9, 2025

ikayaniaamirshahzad@gmail.com

What the history of the web can teach us about the future of AI · Explosion

Recent advancements in AI are exciting, and will surely have a significant, yet uncertain impact on the future. I think there is a lot we can learn from another groundbreaking technology: the web. In this blog post, I’ll look at what the history of the web can teach us about the future of artificial intelligence, and what this means for developers, models, open source and regulation. About this post This blog post is based on a keynote I gave at PyCon+Web on Jan 25, 2025. You can view the slides here. My first introduction to programming was when I discovered

March 9, 2025

ikayaniaamirshahzad@gmail.com

FLUX fine-tunes are now fast

You can fine-tune FLUX on Replicate with your own data. We’ve made running fine-tunes on Replicate much faster, and the optimizations are open-source. This builds upon our work from last month, where we made the FLUX base models much faster. Running a fine-tune is now the same speed as the base model: In addition, the first time you run a fine-tune, it’ll take a bit of time to load the model. That’s usually about 2.5 seconds. Once it’s been loaded, we will attempt to route your requests to an instance that already has it loaded, and it will run as

March 9, 2025

ikayaniaamirshahzad@gmail.com

Text Labeling and Image Resolution with the Monkey Chat Vision Model and DigitalOcean+Paperspace GPUs 🐒

Vision-language models are among the advanced artificial intelligence AI systems designed to understand and process visual and textual data together. These models are known to combine the capabilities of computer vision and natural language processing tasks. The models are trained to interpret images and generate descriptions about the image, enabling a range of applications such as image captioning, visual question answering, and text-to-image synthesis. These models are trained on large datasets and powerful neural network architectures, which helps the models to learn complex relationships. This, in turn, allows the models to perform the desired tasks. This advanced system opens up

March 9, 2025

ikayaniaamirshahzad@gmail.com

Implementing Agent Search with LangGraph for Smarter Knowledge Retrieval

Editor’s note: this is a guest post from our friends at Onyx. As LangGraph has matured, we’ve seen more and more companies (Klarna, Replit, AppFolio, etc) start to use it as their agent framework of choice. We thought this was a great blog describing in detail how that evaluation is done. You can read a version of this post on their blog as well. By Evan Lohn, Joachim Rahmfeld At Onyx, we are dedicated to expanding the knowledge and insights users can gain from their enterprise data, thereby enhancing productivity across job functions. So, what is Onyx? Onyx is an

March 9, 2025

ikayaniaamirshahzad@gmail.com

How Language Models Work

The world has changed considerably since our last “think week” five months ago—and so has Every. We’ve added new business units, launched new products, and brought on new teammates. So we’re taking this week to come up with new ideas and products that can help us improve how we do our work and, more importantly, your experience as a member of our community. In the meantime, we’re re-upping four pieces by Dan Shipper that cover basic, powerful questions about AI. (Dan hasn’t been publishing at his regular cadence because he’s working on a longer piece. Look out for that in

March 9, 2025

ikayaniaamirshahzad@gmail.com

2025 AI Diffusion Export Controls – Microsoft Regulatory Capture, Oracle Tears, Impacts Quantified, Model Restrictions – SemiAnalysis

The US government lobbed the largest salvo in the new technology cold war with its new Framework for Artificial Intelligence Diffusion. These new export restrictions are completely unprecedented in scope and scale, with many calling the efforts overzealous or misguided. The regulation at its core is targeted at preventing China from accessing AI compute to build frontier models. The prevailing rationale within the US government is that AI progress has become so rapid, that access to compute to build and improve these models over the next few years will decide the fate of the next global order for decades to

March 9, 2025

ikayaniaamirshahzad@gmail.com

What’s new in the world of LLMs, for NICAR 2025

What’s new in the world of LLMs, for NICAR 2025 8th March 2025 I presented two sessions at the NICAR 2025 data journalism conference this year. The first was this one based on my review of LLMs in 2024, extended by several months to cover everything that’s happened in 2025 so far. The second was a workshop on Cutting-edge web scraping techniques, which I’ve written up separately. Here are the slides and detailed notes from my review of what’s new in LLMs, with a focus on trends that are relative to data journalism. # I started with a review of

March 9, 2025

ikayaniaamirshahzad@gmail.com

Real-time Bot Detection with BERT and Deephaven

Large language models like ChatGPT have taken the world by storm. There is no question that they have already changed the face of technology, and will continue to improve every year. Humans still make decisions based on information found on the internet, and a growing pool of AI-generated pseudo-information and misinformation is making it more difficult to distinguish fact from fiction. It’s not unreasonable to speculate that in the near future, the only things capable of detecting whether a piece of content was AI-generated will be other AI systems. Building and deploying such systems is not an easy task. They