Wes Roth tests OpenAI Astra across long-running computer-use tasks after receiving access to the model. He has it create game assets, build and animate objects in Blender, assemble projects in Unreal Engine and Unity, add generated audio and play through the result to check whether the experience works.
Roth says the same system created a controller for RimWorld, ordered groceries through Instacart and edited a video by removing pauses. He also demonstrates voice interaction inside an active project and argues that these workflows go beyond ordinary code generation because the model can move between applications and evaluate its own output.
The strongest game was still a rough first pass with basic level design, but Roth considers the result unusually complete for roughly two hours of autonomous work. He also warns that agents operating overnight can reach browsers and sensitive systems, so he removed stored profiles and restricted access before leaving them running.
Watch on YouTube
