Hacking an old pager with AI
A developer describes setting up an old pager as a Twitter notification device using modern cloud services. The system routes Twitter API events through Cloudflare Workers, Resend email service, and Gmail to finally deliver notifications to the pager's email address.
Summary
The speaker explains a creative hack that connects a legacy paging network called Spoke to Twitter notifications. Spoke is one of the last remaining paging networks and comes pre-configured with both an email address and phone number. The developer set up a multi-step pipeline to receive Twitter interactions on this outdated pager. The workflow begins when any interaction with the speaker's Twitter account or tweets triggers an API event. This event is sent to a Cloudflare Worker, which processes it and forwards it to Resend, an email service. Resend then sends the email from a custom domain to a Gmail account, since the pager's native email address cannot accept custom domain emails. Finally, the Gmail account forwards the message to the pager's email address, where it displays on the device. The speaker acknowledges the system is outdated but functional, requiring multiple intermediary steps to bridge the gap between modern social media APIs and legacy paging infrastructure.
Key Insights
- Spoke is described as the one remaining paging network still in operation
- The pager comes pre-configured with both a network email address and phone number, requiring no manual setup for basic functionality
- The pager's native email address has restrictions and cannot accept emails from custom domains, necessitating a Gmail intermediary
- Twitter interactions are funneled through a Cloudflare Worker that acts as the initial processing layer for all API events
- The complete notification pipeline requires at least four separate services (Cloudflare, Resend, Gmail, and the pager network) to function end-to-end
Topics
Transcript
[0:00] There is one paging network left and it's called Spoke. And that's what I did for this. It comes set up with a network. It got comes set up with an email address and a phone number. So, I have it set up as a Twitter pager. I use the Twitter API to send notifications to my Resend email and then it sends it to a Gmail account because the email address that comes with the pager doesn't accept new custom domain emails. [music] It's very outdated. But, the Twitter pager I'll kind of walk you [0:30] through it here. So, every interaction that anyone has with my Twitter account or my tweets get sent as an API event…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
How (and why) to build a personal API
The conversation explores the concept of personal APIs that store individual preferences like favorite restaurants and coffee orders, enabling others to make thoughtful gestures without asking. The discussion evolves to envision AI agents autonomously accessing these APIs to perform personalized tasks like making reservations.
Opus 5: too timid?
The speaker criticizes Opus 5 for being excessively cautious and indecisive, constantly asking for human permission or approval rather than taking action. Even when faced with simple tasks like fixing a one-line merge conflict, Opus 5 deferred to the original branch owner's preferences, requiring the speaker to repeatedly push it to make autonomous decisions.
GPT-5.6's video editing via Codex is genuinely one of my favorite new workflows
A product manager describes using GPT-5.6 with Codex to automate video editing for social media clips. By simply dragging a file and providing natural language instructions, the AI generated five polished, fast-paced hype videos from a long conference talk recording, dramatically reducing the time-intensive manual clipping process.
Theoretically Intelligent vs. Practically Effective: Why GPT-5.6 Sol Beats Fable for Product Work
An executive contrasts two AI models (Fable and Soul/GPT-5.6 Sol), arguing that Soul is superior for product work because it prioritizes practical effectiveness over theoretical intelligence. The speaker values the ability to ship products to customers and understand end-user goals over theoretical sophistication.
Build a harness when the same workflow needs the same setup and the same outcomes, every time
Building a harness for repetitive workflows allows you to be more prescriptive about job execution, resulting in greater efficiency, consistency, and better outcomes. Rather than explaining requirements to an AI agent each time, a harness lets you use a simpler interface like pasting a link while the agent already understands the intended task.