Super Study Guide: Transformers & Large Language Models: http://
amzn.to/3SW6YYm by @afshinea & @shervinea Beautifully presented, excellent content, timely, thorough, educational #LLMs #MachineLearning #AI #GenAI #DataScience #DataScientist #GenerativeAI
LLMS
-
Super Study Guide for Transformers and Large Language Models
By
–
-
LLMs enable trivial click-through tasks via text messages
By
–
I think LLMs are such an interesting tool to build into very complicated apps because the first use cases people will do are the things they can already do ~trivially by clicking through screens, except now with a text message form factor.
-
Mercury’s Command feature tested with wire transfer, works on first try
By
–
Took Mercury's new Command feature out for a test spin with approximately the scariest thing you can do in a bank account, asking for a wire out, and it worked on the first try. Nice UX on upgrading from chatting-with-an-LLM interface to embedded this-is-fully-engineered flow.
-
Plain RAG with good chunking outperforms graph and agentic RAG
By
–
Honestly plain RAG with good chunking still wins most builds, graph and agentic RAG only earn their keep once retrieval is genuinely your bottleneck.
-
Rent the model, own the system: integration and observability compound
By
–
"Rent the model, own the system" is the cleanest version of this I've seen, the integration and eval and observability layer is the part that actually compounds.
-
Per-task routing becomes default, single model apps feel dated
By
–
Per-task routing is becoming the default, locking your whole app to one model already feels dated.
-
Self-Prompting Systems: Beyond the Prompt Itself
By
–
"Build a system that prompts itself" really lands, writing the prompt was never the hard part, it's everything you wrap around it.
-
Multi-trillion-parameter open-source models coming soon to lower token pricing via Jevons paradox
By
–
Also, other multi-trillion-parameter open-source models are landing soon, from what I hear. It's going to be awesome for token pricing and riding the Jevons paradox.
-
Errata: Brave integrated into DINUM Assistant with LLM and web search separation
By
–
ERRATA: Someone just explained to me that Brave is here called at the level of "The Assistant", the agent developed by DINUM. They separated the LLM model from web search queries in order to have more flexibility (which is smart and consistent, by the way). >>> So here, x.com/DFintelligence…
-
18% of US Adults Very Confident in AI Tools, Gap Found
By
–
18% of US adults overall are "extremely/very confident" in their ability to use AI tools like ChatGPT, Gemini, Claude. That is 37% of all AI users. There is a massive gap between superusers and standard users – I suspect at least 50% of that 'very confident' group are nowhere