Dexa/Kyle Polich

Published Oct 29, 2024

Graphs for HPC and LLMs

Senior researcher Maciej Besta delves into the transformative role of graph theory in high-performance computing and large language models, spotlighting the Graph of Thought model's potential to streamline problem-solving and improve reasoning and output quality.

Episode Highlights

Topics covered

Questions from this episode

- What's next in large language models (LLMs)?
  Asked by 33 people
- What techniques are used with large language models (LLMs)?
  Asked by 23 people
- What are the next advancements in large language models (LLMs)?
  Asked by 21 people
- Can you share more examples of breaking large tasks into smaller steps?
  Asked by 11 people
- What is the best insight on prompt engineering and engaging large language models (LLMs)?
  Asked by 11 people
- How are prompts used in AI models?
  Asked by 10 people
- What are some examples of breaking large tasks into smaller steps?
  Asked by 7 people
- Can you give examples of effective prompts?
  Asked by 5 people
- How do you break tasks into smaller steps?
  Asked by 4 people
- What makes a prompt effective?
  Asked by 2 people
- What will be the next development in AI? Currently, large language models are limited in their reasoning ability. Will the improvement of reasoning ability provide more help in the next step?
  Asked by 2 people
- What are practical tips for prompt engineering?
  Asked by 2 people
- Tell me more about decomposing abstractions
  Asked by 2 people
- What techniques are effective for prompting models to create summaries or other outputs?
  Asked by 2 people
- What are AI reasoning breakthroughs?
  Asked by 2 people

Episode Highlights

Related Episodes

Graph Databases and AI
Answers 383 questions
Graphs and ML for Robotics
Answers 383 questions
Graph Transformations
Answers 383 questions
Customizing a Graph Solution
Answers 383 questions
GraphText
Answers 383 questions
Fraud Detection with Graphs
Answers 383 questions
Auditing LLMs and Twitter
Answers 383 questions
LLMs for Data Analysis
Answers 383 questions
Visualization and Interpretability
Answers 383 questions
Social Networks
Answers 383 questions
Learn to Code
Answers 383 questions
Quantum Computing
Answers 383 questions
The Computational Complexity of Machine Learning
Answers 383 questions
Complexity and Cryptography
Answers 383 questions
Process Mining with LLMs
Answers 383 questions