The hottest Knowledge Graphs Substack posts right now

Agent sprawl is a real governance risk because most organizations can’t reliably list which AI assistants are live or what data and actions they can access.
You need to know for each assistant what it can read, change, and trigger, who owns it, and whether actions are logged so you can make governance decisions.
Modeling assistants, connectors, systems and policies as relationships (e.g., in a knowledge graph) lets you ingest partial truths, answer risk queries quickly, and apply controls like per-user SSO, logging, and human approval gates on a repeatable basis.

Large Language Models (LLMs) can create useful text but often struggle with specific knowledge-based questions. They need better ways to understand the question's intent.
Retrieval-augmented generation (RAG) systems try to solve this by using extra knowledge from sources like knowledge graphs, but they still make many mistakes.
The Mindful-RAG approach focuses on understanding the question's intent more clearly and finding the right context in knowledge graphs to improve answers.

Knowledge graphs can enhance large language models (LLMs) by providing structured factual knowledge about the world, improving their reasoning abilities and usefulness for real-world applications.
Augmenting pre-training of LLMs with knowledge graphs through techniques like integrating into training objectives and model inputs can create models proficient in language generation and factual knowledge.
Enterprises can leverage their data to enhance LLM applications with knowledge graphs, as tools exist to automatically turn semi-structured data into structured knowledge graphs.

The internet is a network of maps, not oracles
New AI technologies are better understood as maps, not oracles
Tools like Large Language Models can reveal biases and structures in knowledge spaces

AI chips are evolving to meet the demands of models, like the focus on non-Nvidia backends making strides with software stacks such as PyTorch 2.0 and Triton.
Knowledge graphs are escalating in importance for AI applications due to their ability to provide structured data representation, aiding in better comprehension and use of information.
Anticipation is growing for AI regulations in 2023; teams are advised to prepare for regulatory changes in data and AI by consulting with experts and staying informed.

Get a weekly roundup of the best Substack posts, by hacker news affinity:

Language models can sometimes output inaccurate information due to initial mispredictions.
In AI, achieving justified true beliefs does not necessarily equate to knowledge.
Integrating knowledge graphs with language models can enhance the accuracy of responses.

Model monitoring is crucial for robust machine learning applications to ensure they perform as expected over time
Delta Live Tables simplifies the ETL lifecycle by allowing data engineers to build pipelines using SQL queries
Greykite, an open source library for time series forecasting, offers speed and flexibility but requires investment to learn for production use

Build data apps using markdown and SQL with Evidence framework, offering a way to create polished data products.
Explore the future synergy of knowledge graphs and large language models (LLMs) for enhanced technologies.
Engage with the latest in data engineering by checking out a full exploration of the open-source data engineering landscape for 2024.

The website displays knowledge graphs generated by ChatGPT.
Different types of knowledge graphs shown include Large Language Model, Clinical Trial, and Financial Markets.
The website offers prompts to create the displayed knowledge graphs.