After Hours: A 3D City Rendered in ASCII

Matthew Berman shows a generated city made of text characters and says it was built with Astra.

MBMatthew Berman登壇者 · Forward Future
チャンネル
Matthew Berman
公開日
2026年9月14日
動画
0:31
読了時間
1 分
スライド
1
原文
英語
YouTube で開く
スクロールすると動画は右下に小さくなって再生を続けます。字幕は閲覧言語に合わせて切り替わります。
閲覧言語2 言語で読めます
この記事はまだ日本語に翻訳されていないため、英語の原文を表示しています。
要約

30 秒でわかる

In this short demo, Matthew Berman walks through After Hours, a 3D city rendered with ASCII characters. He says he used Astra and roughly two prompts to build it, and describes the environment as generating new scenery as he walks. The clip does not independently establish an infinite world.

  1. 1A city made of charactersBerman says Astra created the 3D city, called After Hours, using ASCII characters.
  2. 2A brief creation processHe estimates that it took two prompts.
  3. 3A generative environmentHe points to people and rain and says the world continues to populate as he walks.

ポイント

  1. After Hours renders a city scene using ASCII characters.
  2. Berman says he used Astra and approximately two prompts to create it.
  3. The short shows a rainy city with moving people.
  4. Berman says the world generates more scenery as he walks; the clip does not test infinite extent.
全文

チャプターごとに整えた全文を読む

文字起こしのみ
01

After Hours in ASCII

Berman introduces a 3D city made of characters. He says he created it with Astra.

I had Astra create a 3D city using only ASCII characters. It’s called After Hours. You can walk through it, and if you look closely, the whole scene is made of little characters.

02

Walking through the city

He estimates it took two prompts and shows a rainy, populated environment. He says the scene generates as he walks.

ASCII city scene
スライド 1 / 1ASCII city sceneThe demonstration renders buildings and a street with text characters.

I think this took two prompts. People are walking around and it’s raining. The environment is generative: I say I can keep walking and it will keep populating the world, though the short clip does not establish an infinite extent.

同じチャンネルの記事

スライド 12 枚34:21EN
Matthew Berman· 2026年10月27日Matthew 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 Safetyエンタープライズ AI+2
スライド 6 枚25:50EN
Matthew Berman· 2026年10月24日Kimi 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
スライド 2 枚32:20EN
Matthew Berman· 2026年10月23日Who 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
スライド 6 枚1:03:37EN
Matthew Berman· 2026年10月23日Matthew Berman’s Team Tests Kimi K3.1 on Animation, Games, and ChartsMatthew Berman, Alex, Brian · Forward FutureA live team AMA turns into an informal test of Kimi K3.1, from personal-agent workflows to motion graphics, a browser game, and a benchmark chart.コーディングエージェントGenerative media評価(Evals)+2
0:53EN
Matthew Berman· 2026年10月22日Sam Altman on AI and the Discovery of New KnowledgeSam Altman · OpenAIAltman expects progress in mathematical discovery to extend to biology, materials and energy.AI for scienceMathematicsComputational Biology+1
スライド0:22EN
Matthew Berman· 2026年10月21日A Robot Bodyguard Video Shows Dramatic Rescue ScenariosMatthew Berman · Forward FutureMatthew Berman reacts to a short robot demonstration depicting fighting and vehicle-rescue scenarios.Robotics評価(Evals)