Dexa/Kyle Polich

Published Jan 29, 2025

Auditing LLMs and Twitter

Kyle Polich dives into the world of graph theory with experts Gilles Tredan and Erwan Le Merrer, illuminating its power to decipher shadow banning on Twitter and hallucinations in large language models, while unveiling innovative auditing techniques to enhance transparency in social media platforms and distributed systems.

Episode Highlights

Topics covered

Questions from this episode

- Tell me something unique about large language models in the context of the episode Stephen Wolfram: ChatGPT and the Nature of Truth, Reality & Computation | Lex Fridman Podcast #376 and the clip Language Model Limitations
  Asked by 24 people
- What is the algorithmic perspective?
  Asked by 5 people
- What are some techniques for evaluating trees of output from large language models (LLMs) in the episodes Graphs for HPC and LLMs and Understanding Thought Structures?
  Asked by 3 people
- What is the shadow side of social media as discussed in the episode 156: Jaron Lanier | Why You Should Unplug from Social Media for Good and the clip Social Networks and Bad Actors?
  Asked by 3 people
- Is this large language model (LLM) subject to hallucinations?
  Asked by 2 people
- What are distributed systems?
  Asked by 2 people

Episode Highlights

Related Episodes

Graphs for HPC and LLMs
Answers 383 questions
Graph Databases and AI
Answers 383 questions
LLMs for Data Analysis
Answers 383 questions
LLMs in Social Science
Answers 383 questions
Fraud Detection with Graphs
Answers 383 questions
Process Mining with LLMs
Answers 383 questions
Graphs and ML for Robotics
Answers 383 questions
Social Networks
Answers 383 questions
I LLM and You Can Too
Answers 383 questions
Auditing Algorithms
Answers 383 questions
Mapping Dialects with Twitter Data
Answers 383 questions
Emergent Deception in LLMs
Answers 383 questions
Shadow Profiles on Social Networks
Answers 383 questions
LLMs for Evil
Answers 383 questions
LLMs in Music Composition
Answers 383 questions