A Five-Day Astra Run Builds a City Simulation

Matthew Berman shows a city-building game he says Astra produced over five days, and notes that the project remained unfinished.

MBMatthew BermanPonente · Forward Future
Canal
Matthew Berman
Publicado
15 sept 2026
Vídeo
0:35
Lectura
1 min
Diapositivas
1
Original
inglés
Abrir en YouTube
Al desplazarte, el vídeo se reduce a la esquina inferior derecha y sigue reproduciéndose. Los subtítulos siguen tu idioma de lectura.
Idioma de lecturaDisponible en 2 idiomas
Este artículo aún no está en español, así que se muestra el original en inglés.
RESUMEN

En 30 segundos

In this short demonstration, Matthew Berman says he used the /goal command with Astra to build a playable city simulation over five days. He points out buildings, moving people and traffic, while noting that the project was still unfinished when he shipped it.

  1. 1A five-day runBerman says he used /goal with Astra and it ran for five days creating assets.
  2. 2City infrastructureHe names a fire station, police station, hospital, nuclear plant and university among the buildings.
  3. 3An unfinished simulationHe points to pedestrians and cars, while saying he shipped the project before it was complete.

Conclusiones

  1. Berman says an Astra /goal run continued for five days and created individual assets.
  2. The displayed city includes buildings, pedestrians and traffic.
  3. He describes the game as playable but says it was not finished after the five-day run.
TEXTO COMPLETO

Lee el texto editado por capítulos

Solo la transcripción
01

Building the city

Berman says Astra generated individual assets across a five-day run. He points out several types of city infrastructure.

City simulation interface
DIAPOSITIVA 1 / 1City simulation interfaceThe demonstration shows a built-up city alongside its construction controls and indicators.

I used /goal with Astra, and it ran for five straight days, creating each asset one by one. The city includes a fire station, police station, hospital, nuclear energy plant and university.

02

Showing the simulation

He describes a playable city with people and traffic. He says the project was still unfinished when he shipped it.

This is a playable city-building game. You can see people walking and cars driving through traffic. After five days it still wasn’t finished, but I decided I had to ship it.

Más de este canal

12 diapositivas34:21EN
Matthew Berman· 27 oct 2026Matthew 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 SafetyIA empresarial+2
0:26EN
Matthew Berman· 25 oct 2026Sam 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
2 diapositivas0:36EN
Matthew Berman· 25 oct 2026Kimi 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.EvaluacionesAgentes de programaciónOpen-weight models
2 diapositivas0:21EN
Matthew Berman· 24 oct 2026An 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.BenchmarksEvaluacionesGenerative media
6 diapositivas25:50EN
Matthew Berman· 24 oct 2026Kimi 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
2 diapositivas32:20EN
Matthew Berman· 23 oct 2026Who 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