Skip to main content
How I AI

GPT-6 Astra is a banger - here’s everything I’ve built

32 min episode · 2 min read

Episode

32 min

Read time

2 min

Topics

Remote Work, Design & UX, Software Development

AI-Generated Summary

Key Takeaways

  • Computer Use for Complex UI: GPT-6 Astra navigates node-based workflow builders, CRM pipelines, and design tools like Flora and Figma without human input. Tasks previously requiring an hour of manual dragging, clicking, and prompt-writing—such as building lead-routing logic with conditional Slack outputs—now complete hands-free in minutes. Prioritize computer use for any repetitive UI-heavy workflow.
  • Browser-Based QA Automation: Use Astra's browser control to run QA on staging branches autonomously. In one session, it ran for one hour and forty-five minutes on a chat application, inspecting the browser console for error logs, triggering race conditions deliberately, and self-correcting issues—replacing a tedious manual testing process that most developers skip or compress.
  • One-Shot Complex Data Pipelines: Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP—all in approximately three prompts. Previous models failed on insight quality despite correct architectural guidance.
  • Hardware Hacking via Reverse Engineering: Astra successfully reverse-engineered the proprietary pixel protocol of a DivoomMini 2 Bluetooth speaker—a task that stalled on earlier models—then built a live drawing app, a CLI interface, and a Codex notification hook for the device. Targeting locked consumer hardware with no API is now a viable one-session project.
  • 3D Game Generation in Blender: Astra generates functional 3D games in Blender from a single prompt. A dress-up game with swappable clothing, accessories, skin tones, and a runway animation rendered in one shot. A separate children's educational app became a navigable 3D world with keyboard controls in one prompt—no prior 3D coding required from the developer.

What It Covers

Host Claire reviews GPT-6 Astra after early access, demonstrating its capabilities across computer use, browser automation, coding, and 3D asset generation. She walks through five real builds—CRM workflow automation, thumbnail generation, hardware hacking, a product intelligence wiki, and a Blender fashion game—completed in days using the new model.

Key Questions Answered

  • Computer Use for Complex UI: GPT-6 Astra navigates node-based workflow builders, CRM pipelines, and design tools like Flora and Figma without human input. Tasks previously requiring an hour of manual dragging, clicking, and prompt-writing—such as building lead-routing logic with conditional Slack outputs—now complete hands-free in minutes. Prioritize computer use for any repetitive UI-heavy workflow.
  • Browser-Based QA Automation: Use Astra's browser control to run QA on staging branches autonomously. In one session, it ran for one hour and forty-five minutes on a chat application, inspecting the browser console for error logs, triggering race conditions deliberately, and self-correcting issues—replacing a tedious manual testing process that most developers skip or compress.
  • One-Shot Complex Data Pipelines: Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP—all in approximately three prompts. Previous models failed on insight quality despite correct architectural guidance.
  • Hardware Hacking via Reverse Engineering: Astra successfully reverse-engineered the proprietary pixel protocol of a DivoomMini 2 Bluetooth speaker—a task that stalled on earlier models—then built a live drawing app, a CLI interface, and a Codex notification hook for the device. Targeting locked consumer hardware with no API is now a viable one-session project.
  • 3D Game Generation in Blender: Astra generates functional 3D games in Blender from a single prompt. A dress-up game with swappable clothing, accessories, skin tones, and a runway animation rendered in one shot. A separate children's educational app became a navigable 3D world with keyboard controls in one prompt—no prior 3D coding required from the developer.

Notable Moment

During a live recording session, the designer became unavailable for thumbnail creation. Astra was handed control of Figma cold—a tool where computer use had previously failed entirely—and produced a publish-ready YouTube thumbnail without any human intervention, completing the task before the episode finished recording.

Know someone who'd find this useful?

Episode Transcript

We are going to the stars today because, yes, today, GPT six Astra is live. Well, it's live for Daybreak customers. It will be live for the rest of us very soon. I was lucky enough to get some early access to test the model, and this has been the model in the last six months. And, you know, maybe I sound like a broken record, but this is the one that has made me actually feel more ambitious. It has crushed some of my standing tasks that Fable couldn't figure out. Even my beloved five six soul couldn't figure out. This model, GPT six, one shot a bunch of them. I'm gonna tell you what this model is, what OpenAI says it's great at, and I'm gonna show you some pretty incredible things I've built with it, including, yes, hacking this dumb computer again. Let's get to it. Okay. I don't wanna spend too much time on the blog post. We can link to it in the show notes. You all can go read it. TLDR, state of the art on basically everything. We got the science, math, coding, knowledge work, not being annoying, being fast, computer use, all the things. So OpenAI is positioning it as its most intelligent and aligned model. Huge jumps, particularly on frontier math, a big jump there in mathematical ability. The big thing that they're calling out is computer use and the use of software. So you're gonna see this in today's episode, but it is so good at computer use. Not just browsers, but Excel, Unity, Power BI, Blender, Jupyter, document editors, like kind of everything. So we're back. SaaS is back. Product's back. Buttons are back because now Astra can use it. It's really good at producing work artifacts. They've done a lot of work to make work artifacts match your style, match your brand, match your voice, etcetera. And then again, autonomy, steering, all that kind of stuff is is very good. They've really focused a lot on kind of time saving on common tasks again because of computer use. And so this is a little, like, sneak peek into, I think, like, we're all spending a lot of money on tokens, and these models are feeling pressure to come up with an ROI model. And and I think you're gonna hear a lot about them talking about Astra in terms of computer use and time saving, right? Like apartment hunting can go down to ten minutes from six hours. I'll show you an example of generating thumbnails. Again, something that takes us like an hour down to a couple of minutes, completely hands free. And so, a a lot faster, a lot more efficient, and kind of able to do what they say real work. They really call out presentations, spreadsheets, documents, and software as great use cases for Astra, but let's look a little bit at kinda some of the numbers. So Automation Bench, again, double Soul's reported …

Get the full transcript (5,539 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all How I AI transcripts →

You just read a 3-minute summary of a 29-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.

Tools

  • GPT-6 AstraRecommended

    by OpenAI

    Host Claire reviews GPT-6 Astra after early access, demonstrating its capabilities across computer use, browser automation, coding, and 3D asset generation.
  • GPT-6 Astra navigates node-based workflow builders, CRM pipelines, and design tools like Flora and Figma without human input.
  • FigmaRecommended
    During a live recording session, the designer became unavailable for thumbnail creation. Astra was handed control of Figma cold—a tool where computer use had previously failed entirely—and produced a publish-ready YouTube thumbnail without any human intervention.
  • Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP.
  • Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP.
  • Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP.
  • Astra resolved a multi-month engineering challenge by ingesting unstructured data from Intercom, Linear, Granola, and GitHub, deduplicating insights, generating prioritized product recommendations, and producing an auto-updating product wiki exposed via MCP.
  • BlenderRecommended
    Astra generates functional 3D games in Blender from a single prompt. A dress-up game with swappable clothing, accessories, skin tones, and a runway animation rendered in one shot.

Gear

  • by Divoom

    Astra successfully reverse-engineered the proprietary pixel protocol of a DivoomMini 2 Bluetooth speaker—a task that stalled on earlier models—then built a live drawing app, a CLI interface, and a Codex notification hook for the device.

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Software Engineering Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into How I AI.

Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime