The surest sign AI is becoming real is that it's now generating $$$ for real companies doing boring things, like customer service. (Related: it has lured @ZUrlocker out of his 20th retirement to help grow another billion-dollar software company.)
SOFTWARE
-
Gradio 5.0 enables real-time streaming with minimal code
By
–
Building real-time interaction was hard, because python web frontend and streaming doesn't mix very well. Now you can do that with exactly 250 lines of code thanks to the upcoming Gradio 5.0. Over the weekend we figured we can do a real-time streaming demo with it and
-
LFM Architecture: Memory-Efficient LLM for Long Contexts
By
–
The LFM architecture is also super memory efficient. While the KV cache in transformer-based LLMs explodes with long contexts, we keep it minimal, even with 1M tokens. This unlocks new applications, like document and book analysis, directly in your browser or on your phone.
-
Liquid AI Launches Three LLMs with SOTA Performance and Edge Optimization
By
–
This is the proudest release of my career 🙂 At @liquidai
, we're launching three LLMs (1B, 3B, 40B MoE) with SOTA performance, based on a custom architecture. Minimal memory footprint & efficient inference bring long context tasks to edge devices for the first time! -
Perplexity dynamic autosuggestions now widely available, previously experimental
By
–
ICYMI: Perplexity dynamic autosuggestions seem to be widely available now. Previously they were experimental and were working only with Sonar models.
-
MATLAB R2024b Released: 1900+ Updates Including Deep Learning
By
–
Have you downloaded R2024b yet? MATLAB R2024b has 1,900+ updates! Highlights: MATLAB Package Manager Data sonification Improved ODE solving New plot types Deep learning segmentation More in the blog https://
spr.ly/6012o2cco Let us know what you think! -
90% of websites will become conversational agents via LLMs
By
–
Wait until we have LLMs that work with JavaScript libraries directly in the browser. 90% of the websites we know today will die to be reborn in the form of a 'conversational agent'. No more endless pages and sections that nobody reads.
-
Fine-tuning Small Language Models like Gemma: A Practical Guide
By
–
Fine-tuning & Inference of Small Language Models like Gemma: Introduction Imagine you’re building a medical chatbot, and the massive, resource-hungry large… https://
analyticsvidhya.com/blog/2024/09/f
ine-tuning-inference-of-small-language-models-like-gemma/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #SaaS #CTO #ITDirector #AI #ArtificialIntelligence -
Deploy LLM Chatbot with RAG and Databricks Vector Search
By
–
Take this product tour on RAG + Databricks Vector Search You’ll learn how to deploy an LLM chatbot using RAG + the AI Vector search index on Databricks and how to implement an end-to-end #GenAI application – from data ingestion to model deployment:
-
Software Development: Making Things Worse While Fixing Them
By
–
In German, the word "Verschlimmbessern" means “to make something worse while repairing it.” In English, we call that "software development."