New Release (2nd edition) from @PacktDataML available at https://
amzn.to/4tULP1b RAG-Driven Generative AI โ Build MAS-RAG with DualRAG, GraphRAG, multimodal video pipelines, and Oracle Database 23ai ๐๐ฒ๐ ๐๐ฒ๐ฎ๐๐๐ฟ๐ฒ๐:
Master DualRAG by combining vector search with SQL
GENERATIVE AI
-
New technical guide on RAG-driven Generative AI and graph-based retrieval
By
–
-
RouteLLM: Intelligent Model Routing for Language, Video, and Image Models
By
–
RouteLLM From Abacus AI Routes To The Best Model Based On Your Prompt – GPT 5.5 xHigh
– Opus 4.7 – Gemini 3.1
– Seedance 2.0
– GPT Image 2 100 top language, video and image models all in one place! -
Blog: Recent Developments in LLM Architectures
By
–
Wow, a new blogpost from the GOAT Sebastian Raschka! Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention
-
ChatGPT Image Generation Surpasses 1 Billion Milestone in India
By
–
ChatGPT Images 2.0 India. Already more than 1 billion images created there; awesome to see.
-
Google releases beginner-friendly prompt engineering guide
By
–
9/ Prompting Guide 101 โ by @Google A beginner-friendly resource to master the fundamentals of prompt design. โ https://
services.google.com/fh/files/misc/
gemini-for-google-workspace-prompting-guide-101.pdf
โฆ -
Anthropic Releases Comprehensive Prompt Engineering Guide
By
–
7/ Prompt Engineering Overview โ by @Anthropic A structured guide with best practices, techniques, and tutorials to improve your prompts step by step. โ https://
docs.anthropic.com/en/docs/build-
with-claude/prompt-engineering/overview
โฆ -
Experiments Used GPT-4 and GPT-4o; Newer Models Could Improve Results
By
–
And, yes, our experiments used a mix of GPT-4 & GPT-4o (publishing takes awhile). I think we would see much larger results with more recent models, let alone recent agentic tools.
-
User experience comparing Claude and ChatGPT workflows
By
–
Iโm increasingly using Claude (prob 50/50 now) but ChatGPT still knows me better as Iโve been using it for longer. I did try the move over info prompt which helped but not quite there yet.
-
Using Claude for Zero-Code Front-End Animation
By
–
I don't know if I made this explicit so I'll make this explicit: zero point zero knowledge required of HTML or JS animation techniques to make this work. I'm not even looking at the textual output here. That's Claude's problem; nothing matters except how it displays in Chrome.
-
Optimizing LLM Prompt Length and Workflow Efficiency
By
–
"How long are your prompts for these?" 600 and 900 words for last two, both assuming refinement after initial delivery. One operator at a single keyboard can do several of them during a work day, even assuming downtime as the LLM goes off and cranks for 5 minutes between revs.