The first #PostgreSQL #Edinburgh meetup was a success! Did you miss @vyruss delivering RAGTime with Postgres?
His comprehensive slides on learning about AI power with pgvector and Retrieval-Augmented Generation can be found here:
https://vyruss.org/computing/slides/postgresedi_ragtime_with_postgres.pdf
cc @PostgresEDI
#postgres #ai #aiops #llmops #llm #aiengineering #programming #opensource #tech #dev #devcommunity
Your RAG is lying.
Not because of the model — because retrieval failed. 🤖⚠️
Read this before shipping GenAI to production.
https://medium.com/@rogt.x1997/vector-search-vs-reality-5-retrieval-errors-that-break-enterprise-rag-349abf97502c
#RAG #GenAI #AIEngineering
https://medium.com/@rogt.x1997/vector-search-vs-reality-5-retrieval-errors-that-break-enterprise-rag-349abf97502c
#AIEngineering #linux #opensource
The Linux Moment for AI Has Arrived: MCP, Agents, and the Linux AI Foundation
QCon AI is coming to Boston, June 1-2, 2026.
Get proven architectural patterns for scaling AI in production: MLOps, security, SDLC integration, and business impact from senior practitioners.
Launch pricing ends Dec 9: https://bit.ly/48NC2Az
Local to #Edinburgh? The next #PostgreSQL Edinburgh Meetup is this Thursday, December 11 and you'll be able to catch @vyruss delivering "RAGTime with Postgres: AI Power with pgvector and Retrieval-Augmented Generation".
It's bound to be a great deal of fun - register here if you'd like to attend: https://luma.com/b9kv5fds
Too far to join, but still want to learn about the topic? Let us know 💬
#scotland #postgres #devcommunity #rag #ai #pgvector #llm #aiengineering #programming #engineering
RAG retrieval ko hỏng? Đa phần vấn đề nằm ở xử lý dữ liệu. Nhiều người dành cả tuần chỉnh tối ưu mô hình/truy xuất nhưng bỏ qua lỗi từ bước tiền xử lý: dữ liệu được cắt tách, bảng chia đôi, text nhiễu, meta thông tin bị xóa. Kiểm tra 50 đoạn dữ liệu ngẫu nhiên & so sánh file PDF gốc vs kết quả parser để khắc phục. #RAG #AI #MachineLearning #XuLyDuLieu #AIEngineering
I wonder how many edge cases robotaxi companies have missed that put public at risk?
Waymo to Recall Robotaxis Over Failure to Stop for School Buses
https://www.pcmag.com/news/waymo-to-recall-robotaxis-over-failure-to-stop-for-school-buses
OpenAI Just Bought a Company to Make Training Models Less Painful
OpenAI is acquiring Neptune, a startup that helps teams manage, debug, and monitor AI model training at scale. Think experiment tracking, metrics, versioning—the unsexy glue that turns chaotic training runs into reproducible systems.
The next big AI productivity unlock might not be a smarter LLM. It might be better ways to build, track, and ship the ones we already have.
When You Need Clustering or SVM Developers for ML Projects
Not sure when your ML project requires expert help? Clustering specialists and SVM developers can make a huge difference when working with complex datasets, uncovering hidden patterns, or building high-accuracy predictive models.
📌 Read the full article on the Amplework blog: https://www.amplework.com/blog/when-you-need-clustering-or-svm-developers/
#MachineLearning #Clustering #SVM #DataScienceExperts #MLProjects #AIEngineering #PredictiveModels #ScalableML #AIDevelopment
QCon AI New York is officially sold out.
If you missed a spot, the conversation continues at QCon AI Boston, June 1-2, 2026.
Learn more and register at https://bit.ly/4pnRJ8z
Unter Leitung der @uni-magdeburg.de@bsky.brid.gy startet der bundesweit erste hochschulübergreifende Modellstudiengang für #AIEngineering in den Regelbetrieb. link.ovgu.de/Studiengangai
🤖 “𝗝𝘂𝘀𝘁 𝘁𝗮𝗹𝗸 𝘁𝗼 𝗶𝘁.”
Peter Steinberger’s mantra for real-world 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 — and honestly the best AI dev advice I’ve read all year.
A solo dev runs a 300k LOC TypeScript codebase with just a few GPT-5-Codex panes. No wrappers. No harnesses. Just natural language, fast iteration, clean commits.
AI isn’t just an assistant — done right, it’s a team. 💡
#AIEngineering #LLM #OpenAI #AgenticWorkflows #SoftwareEngineering
Just shipped a deep-dive for Java devs who want real stateful LLM apps.
Persistent memory. Sliding windows. Multi-session isolation.
All powered by Quarkus + LangChain4j + JPA.
If you want your AI assistant to remember across pods and restarts, this tutorial will get you there.
🔗 https://www.the-main-thread.com/p/persistent-llm-memory-java-quarkus-langchain4j-tutorial
#Java #Quarkus #LangChain4j #AIEngineering #LLMApps #OpenSource
