In 30 seconds
Matthew Berman introduces Google DeepMind's Genie 3 and imagines prompt-generated video games. Genie 3 generates interactive visual environments, but its research announcement describes limited actions and interaction lasting minutes; the short clip does not establish complete world understanding or a game comparable to GTA 6.
- 1A game predictionBerman speculates that AI could create something like GTA 6; the clip does not demonstrate such a game.
- 2Interactive generated worldsHe introduces Genie 3 as a promptable world model. Google describes generated visual environments rather than proving complete understanding.
- 3Limits of the demonstrationThe technology can produce navigable scenes, but Google documents constraints on actions and interaction duration.
Takeaways
- Genie 3 generates interactive visual environments from prompts.
- Google's 2025 announcement described 720p navigation at 24 frames per second with consistency for a few minutes.
- The model's limited action space and short interaction duration constrain its use as a complete game.
- Berman's predictions about GTA 6 and promptable games are speculation.
Read the edited text by chapter
A prediction about games
Berman speculates about AI-generated games and introduces Genie 3.
Matthew Berman speculates that AI could create something like GTA 6 before the game's release. This is a prediction, not a demonstration that Genie 3 has built an equivalent game.
Promptable environments
He presents Genie 3 as a world model. Its research release describes important action and duration limits.
Berman introduces Google DeepMind's Genie 3 as a promptable interactive world model and says it understands the world. Google describes a system generating navigable visual environments from prompts; a convincing scene does not by itself establish complete physical understanding.
Berman predicts that promptable video games are coming quickly. In its 2025 announcement, Google described 720p interaction at 24 frames per second with consistency for a few minutes, and noted limited actions and challenges with long-running or multi-agent interactions. Those constraints distinguish the demonstrated research system from a full game.
More from this channel
34:21EN
Matthew Berman· Oct 27, 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.
0:36ENMatthew Berman· Oct 25, 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.
25:50ENMatthew Berman· Oct 24, 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.
32:20ENMatthew Berman· Oct 23, 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.
1:03:37ENMatthew Berman· Oct 23, 2026Matthew 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.
0:53ENMatthew Berman· Oct 22, 2026Sam Altman on AI and the Discovery of New KnowledgeSam Altman · OpenAIAltman expects progress in mathematical discovery to extend to biology, materials and energy.