Three GPT-6 Game and World Demos

Matthew Berman briefly shows a navigable low-poly world, an ASCII scene and a city simulation.

MBMatthew Berman연사 · Forward Future
채널
Matthew Berman
게시일
2026년 9월 3일
영상
0:37
읽기
1분
슬라이드
3
원문
영어
YouTube에서 열기
스크롤하면 영상이 오른쪽 아래로 작아져 계속 재생됩니다. 자막은 읽기 언어를 따릅니다.
읽기 언어2개 언어로 읽을 수 있음
이 글은 아직 한국어 번역이 없어 영어 원문으로 표시합니다.
요약

30초 요약

In this short video, Matthew Berman presents three demos associated with GPT-6: a small 3D world, an ASCII-rendered world and a city-building simulation. He praises the results, although the short does not provide a detailed evaluation of their completeness or reliability.

  1. 1A small 3D worldBerman shows a low-poly environment that a character can navigate.
  2. 2An ASCII worldHe shows a 3D scene rendered with ASCII characters and says it extends indefinitely.
  3. 3City simulationHe describes a SimCity-like game and zooms in on the city and its people.

핵심 정리

  1. The first demo shows a navigable low-poly world.
  2. The second uses ASCII characters to render a 3D scene.
  3. The third shows a city simulation with buildings and moving people.
  4. The presenter’s claim that everything works is not independently established by the short demonstration.
전문

챕터별로 다듬은 전문 읽기

원본 자막만 보기
01

Two navigable worlds

Berman introduces GPT-6 demos. He shows a low-poly environment and an ASCII-rendered 3D scene.

Navigable low-poly world
슬라이드 1 / 3Navigable low-poly worldThe demonstration shows a small spherical environment with a character.
ASCII-rendered 3D scene
슬라이드 2 / 3ASCII-rendered 3D sceneA street scene is rendered using characters.

GPT-6 is here. Look at this: a little low-poly 3D world you can navigate with a character. There’s also a 3D world made entirely of ASCII characters that I say goes on indefinitely.

02

A city-building demo

He shows a SimCity-like simulation with buildings and people. The short does not verify the completeness of its features.

City simulation
슬라이드 3 / 3City simulationThe demo shows a built-up city from above.

The most impressive demo to me is a SimCity-like city. I say everything works, and when I zoom in you can see people walking around the buildings. The short gives a glimpse of the simulation rather than a comprehensive test of all its features.

같은 채널의 다른 글

슬라이드 12장34:21EN
Matthew Berman· 2026년 10월 27일Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.AnthropicAI Safety엔터프라이즈 AI+2
0:26EN
Matthew Berman· 2026년 10월 25일Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.Human-AI CollaborationFuture of WorkAI Strategy
슬라이드 2장0:36EN
Matthew Berman· 2026년 10월 25일Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.평가(Evals)코딩 에이전트Open-weight models
슬라이드 2장0:21EN
Matthew Berman· 2026년 10월 24일An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.Benchmarks평가(Evals)Generative media
슬라이드 6장25:50EN
Matthew Berman· 2026년 10월 24일Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.Open-weight modelsBenchmarksAI cost & performance+1
슬라이드 2장32:20EN
Matthew Berman· 2026년 10월 23일Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.Local inferenceOpen-weight modelsAI cost & performance+1