Best practices for building LLM-based applications
During the talk, we will review the existing tools and see how to move from development to production without a headache.
During the talk, we will review the existing tools and see how to move from development to production without a headache.
Many businesses started incorporating Large Language Models into their applications. There are, however, several challenges that may impact such systems. It’s great to be aware of them before you start. During the talk, we will review the existing tools and see how to move from development to production without a headache.
Kacper Łukawski is a Developer Advocate at Qdrant - an open-source neural search engine. His experience is mainly related to data engineering, machine learning, and software design. Recently he’s been exploring the world of similarity learning and vector search.
Encyclopedia Britannica and Merriam-Webster have sued OpenAI for copyright infringement and trademark infringement. The publishers accuse OpenAI of unlawful scraping and reproduction of their content and claim that falsely attributed hallucinations are damaging their reputations as trusted sources.
Nscale raised $2 billion in Europe's largest Series C at a $14.6 billion valuation to accelerate AI infrastructure buildout globally. In parallel, Nscale announced the appointment of Sheryl Sandberg, Nick Clegg, and Susan Decker to its board.
Replit raised $400 million at a $9 billion valuation, effectively tripling its valuation since its last funding round. Replit also launched Agent 4, a faster AI coding agent that can be run in multiple parallel instances and that can handle more complex workflows than its predecessors.
Recent AI translations of Wikipedia articles have been found to contain substantial errors and hallucinations, causing outrage amongst the Wikipedia volunteers tasked with fighting the endless stream of AI slop that threatens the encyclopedia's survival and integrity.
GPT-5.3 Instant, OpenAI's most recent model update, brings improved conversational tone, flow, and relevance after widespread frustration with GPT-5.2's overbearing tone and unwarranted assumptions about its users' intent and emotional states.
SF Bay Area media and education platform focused on AI and Data. As a voice of AI industry, Data Phoenix delivers news, practical knowledge, and helps companies be heard in the community.
Copyright © 2026 Data Phoenix. Published with Ghost and Data Phoenix.
Privacy Policy | Terms of Service | Cookie Preferences
Comments