Inside the Black Box: Cracking AI and Deep Learning

Arshavir Blackwell, PhD

How do Large Language Models like ChatGPT work, anyway? (Powered by Jellypod)

  1. Fine Tuning Lora: It's Not What You Think

    May 15

    Fine Tuning Lora: It's Not What You Think

    When you fine-tune an AI model, what changes inside doesn't predict what changes outside. This week on Inside the Black Box, I break down why — and what it means for anyone auditing or regulating these systems.

    15 min
  2. When Fluent Answers Start Sounding True

    May 2

    When Fluent Answers Start Sounding True

    This episode explores why smooth, coherent language can feel more credible than it is, and how processing fluency, familiarity, and authority cues shape what we believe. It also digs into why conversational AI is especially persuasive, from polished explanations to confident-sounding confabulations.

    15 min
  3. Why Your Brain Believes the Model

    Apr 27

    Why Your Brain Believes the Model

    The Heuristic Loop You Can't Break from Inside

    25 min
  4. When Polished Answers Feel Finished

    Apr 20

    When Polished Answers Feel Finished

    This episode explores fluency-as-validity: the way polished AI responses can make us feel like the work of judgment is already done. It also looks at why large language models are so effective at creating the sensation of clarity, and why mechanistic interpretability may be a way to push back against that enchantment.

    28 min
  5. What Seneca Teaches Us that Marcus Couldn't

    Apr 12

    What Seneca Teaches Us that Marcus Couldn't

    716 features fire on both Seneca and Marcus Aurelius but stay dark for ad copy. The model learned Stoic philosophy, not just an author's style. Plus: why 'inert' features aren't all the same thing.

    17 min
  6. The Pattern Holds for Another Author

    Apr 4

    The Pattern Holds for Another Author

    We trained a fresh LoRA on the letters of Seneca and ran the same analysis pipeline we used on Marcus Aurelius and advertising copy. Every structural finding replicated. The model organizes its adaptation into five clusters: one tight (features moving in lockstep) and four loose (features cooperating more independently). Seneca produced the cleanest clustering we've measured and the strongest workhorse cluster, a group of 141 features encoding philosophical argumentation with a causal effect more than three times stronger than anything in Marcus. Done in collaboration with John Holman.

    16 min
  7. The Pattern Holds

    Mar 30

    The Pattern Holds

    We replicated our Marcus Aurelius findings at a new layer, then threw the whole method at 12 commercial ad copy styles trained into a single LoRA. The patterns held, and the new domain revealed something we couldn't have seen before: the model organizes its adaptations by register family, not by individual style.

    18 min
  8. Cracking Open the Black Box

    Mar 22

    Cracking Open the Black Box

    We opened the 65%. The features that resisted interpretation one at a time turned out to organize into five co-activation clusters with clear thematic identities and causal effects nearly ten times stronger than any individual feature. Second in a series with John Holman.

    11 min
See All (26)

About

How do Large Language Models like ChatGPT work, anyway? (Powered by Jellypod)

Information