---
schema: 1
type: video
title: >-
  Local Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The
  New York Times
description: >-
  An agent runs entirely on your phone, no cloud, and plays Space Invaders,
  perceiving the scene, predicting the aliens, and dodging bullets in a loop.
  Another solves the New York Times mini crossword with a constraint graph that
  backtracks when the fills stop fitting. These are experimental, and the Times
  is emphatic that its actual puzzles are made by people with no AI in the
  games. The hard part is the budget: a local agent has to plan its next move
  inside a single 16 millisecond frame, without draining the battery or starving
  the renderer, or you get jank. Shafik Quoraishee and Joanne Song use that to
  argue accessibility and difficulty should stop being separate toggles. Model
  the game as a continuous negotiation and they become two ends of one dial the
  agent tunes to you in real time: it watches eye gaze and shaky taps, resizes
  controls on the fly, and breaks a keyboard trap the moment it detects one, all
  on the device. Their closing bet is that the future of AI is not one giant
  centralized brain but billions of small local ones, each shaped by the person
  it runs for. Speaker info: - https://x.com/squoraishee -
  https://www.linkedin.com/in/shafik-quoraishee/ -
  https://www.shafikquoraishee.com/ Timestamps: 0:00 - Disclaimers and the
  experimental frame 1:55 - A short history of AI in games 2:49 - Why run the AI
  on the device, not the cloud 4:56 - From reinforcement learning to agentic
  play 7:00 - Demo: an agent playing Space Invaders 8:19 - The on device budget:
  space, time, and energy 11:15 - Demo: solving the mini crossword by
  backtracking 12:33 - Accessibility: from toggles to graded dials 14:40 - The
  agent tuning the game to you in real time 16:28 - What is still needed, and
  billions of local brains
canonical: >-
  https://liquidgold.cc/channel/aidotengineer/explore/video/local-agentic-theory-for-mobile-games-shafik-quorai-110c10111fc5
markdown: >-
  https://liquidgold.cc/channel/aidotengineer/video/local-agentic-theory-for-mobile-games-shafik-quorai-110c10111fc5.md
llms: null
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T06:51:46.264Z'
language: null
children: []
videoId: 418t26CVz-w
durationSeconds: 1084
publishedAt: '2026-07-23T03:00:01.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 185
    endSeconds: 298
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=185'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 298
    endSeconds: 310
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=298'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 310
    endSeconds: 428
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=310'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 440
    endSeconds: 505
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=440'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 516
    endSeconds: 681
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=516'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 516
    endSeconds: 681
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=516'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 516
    endSeconds: 681
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=516'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 681
    endSeconds: 692
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=681'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 769
    endSeconds: 887
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=769'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 769
    endSeconds: 887
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=769'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 898
    endSeconds: 988
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=898'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 898
    endSeconds: 988
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=898'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 898
    endSeconds: 988
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=898'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 998
    endSeconds: 1084
    watch: 'https://liquidgold.cc/watch/418t26CVz-w?t=998'
    heldReason: rights
---


# Local Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The New York Times

An agent runs entirely on your phone, no cloud, and plays Space Invaders, perceiving the scene, predicting the aliens, and dodging bullets in a loop. Another solves the New York Times mini crossword with a constraint graph that backtracks when the fills stop fitting. These are experimental, and the Times is emphatic that its actual puzzles are made by people with no AI in the games. The hard part is the budget: a local agent has to plan its next move inside a single 16 millisecond frame, without draining the battery or starving the renderer, or you get jank. Shafik Quoraishee and Joanne Song use that to argue accessibility and difficulty should stop being separate toggles. Model the game as a continuous negotiation and they become two ends of one dial the agent tunes to you in real time: it watches eye gaze and shaky taps, resizes controls on the fly, and breaks a keyboard trap the moment it detects one, all on the device. Their closing bet is that the future of AI is not one giant centralized brain but billions of small local ones, each shaped by the person it runs for. Speaker info: - https://x.com/squoraishee - https://www.linkedin.com/in/shafik-quoraishee/ - https://www.shafikquoraishee.com/ Timestamps: 0:00 - Disclaimers and the experimental frame 1:55 - A short history of AI in games 2:49 - Why run the AI on the device, not the cloud 4:56 - From reinforcement learning to agentic play 7:00 - Demo: an agent playing Space Invaders 8:19 - The on device budget: space, time, and energy 11:15 - Demo: solving the mini crossword by backtracking 12:33 - Accessibility: from toggles to graded dials 14:40 - The agent tuning the game to you in real time 16:28 - What is still needed, and billions of local brains

Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/local-agentic-theory-for-mobile-games-shafik-quorai-110c10111fc5 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.
