Inside the Black Box: Cracking AI and Deep Learning

Arshavir Blackwell, PhD

How do Large Language Models like ChatGPT work, anyway?

  1. I Told My LLM Not to Say "Empower"

    −4 D

    I Told My LLM Not to Say "Empower"

    In this episode of Inside the Black Box: Cracking AI and Deep Learning, Arshavir Blackwell, PhD, takes engineers and researchers inside the practical mechanics of LoRA, low‑rank adaptation methods that make it possible to fine‑tune multi‑billion‑parameter language models on a single GPU.

    7 min

  2. 9 FEB.

    Beyond the Surface of AI Intelligence

    This episode dives into why judging AI by behavior alone falls short of proving true intelligence. We explore how insights from mechanistic interpretability and cognitive science reveal what’s really happening inside AI models. Join us as we challenge the limits of behavioral tests and rethink what intelligence means for future AI.

    15 min
  3. Unlocking BERTs Hidden Grammar

    3 FEB.

    Unlocking BERTs Hidden Grammar

    Explore how BERT’s attention heads reveal an emergent understanding of language structure without explicit supervision. Discover the role of attention as a form of memory and what it means for the future of AI language models.

    9 min
  4. Cracking the Code of AI Interpretation

    28 JAN.

    Cracking the Code of AI Interpretation

    Dive into how we naturally explain neural networks with folk interpretability and why these simple stories fall short. Discover the journey toward mechanistic understandability in AI and what that means for how we talk about and trust large language models.

    10 min
  5. Decoding GPTs Hidden Circuits

    26 JAN.

    Decoding GPTs Hidden Circuits

    Explore how sparse autoencoders and transcoders unveil the inner workings of GPT-2 by revealing functional features and computational circuits. Discover breakthrough methods that shift from observing raw network activations to mapping the model's actual computation, making AI behavior more interpretable than ever.

    11 min
  6. Decoding Attention and Emergence in AI

    14 JAN.

    Decoding Attention and Emergence in AI

    Explore how attention heads uncover patterns through learned queries and keys, revealing emergent behaviors shaped by optimization. Dive into parallels with natural selection and psycholinguistics to understand how meaning arises not by design but through experience in both machines and brains.

    6 min
  7. When Knowledge Battles Noise in GPT Models

    7 JAN.

    When Knowledge Battles Noise in GPT Models

    Explore how GPT-2 balances fleeting factual recall with generic responses through internal competition among candidate answers. Discover parallels with human cognition and how larger models navigate indirect recall to reveal hidden knowledge beneath suppression.

    7 min
  8. Inside Circuits: How Large Language Models Understand

    1 JAN.

    Inside Circuits: How Large Language Models Understand

    Dive into the world of neural circuits within large language models. In this episode, Arshavir Blackwell unpacks how transformer circuits, attention mechanisms, and high-dimensional geometry combine to create the magic—and limits—of modern AI language systems.

    8 min
Visa alla (18)

Om

How do Large Language Models like ChatGPT work, anyway?

Information