Skip to content
TLexDR
All topics / recommendation systems
Topic
Skim Read Deep
You are reading the free Skim layer. Read unlocks the synthesis and sources.

Recommendation systems

2
episodes
3
thinkers
3h
of conversation
2
books & papers
5
terms defined

The neighbourhood: recommendation systems and the ideas it travels with. Drag to roam, click a star for the episode, click a neighbour to travel.

Drag to roam · scroll to zoom · click a neighbour to travel · click a star for the episode

From foundational to frontier

Climb the spectrum. The most accessible conversations come first.

Start here
ACCESSIBLECOREFRONTIER

The lexicon

Every term the guests lean on, in plain language. Read one in full, or filter to find it.

    What the corpus says

    The throughline across every conversation that touches this idea.

    Michael I. Jordan argues AI is still a proto-field, akin to early chemical engineering, not yet achieving true intelligence.
    Jordan critiques the term 'AI' as misleading, advocating for 'machine learning' to better reflect the field's current capabilities.
    Recommender systems, though not magical, have become a billion-dollar industry crucial for consumer markets.
    Jordan emphasizes decision-making over prediction in AI, challenging the notion that AI's primary value lies in predictive accuracy.
    Jordan highlights the intelligence of markets as a distinct form of intelligence, separate from human cognition.
    YouTube's recommendation system processes over 500,000 hours of new video daily, more than a human could watch in a lifetime.
    YouTube uses collaborative filtering and clustering to offer diverse content recommendations, such as suggesting jazz to science viewers.
    User interactions like likes, dislikes, and comments are key signals in YouTube's algorithm to gauge satisfaction and improve recommendations.
    A-B testing on YouTube involves hundreds of variables to refine viewer experience and optimize algorithm changes.
    Self-supervised learning is seen as a future pathway for video intelligence, but summarizing video content remains largely unsolved.

    Go read

    2 books and papers cited across these episodes.

    For the specialist

    What experts find new

    6 expert-level takeaways for a specialist reader.

    At the frontier

    Still unresolved

    3 open questions flagged across these conversations.

    The thinkers

    Who takes this idea on, by how often they return to it.

    All guests

    Adjacent ideas