← Back to Jason Harvey’s portfolio
What we set out to explore
This experiment explores Pooled, an open-source project that investigates peer-to-peer, browser-based distributed AI inference. The idea is to connect devices so that available resources may be pooled rather than relying on one machine alone.
The aim was to test a Windows desktop and an iPhone as potential peers, understand the connection requirements, and distinguish what the interface reports from what has actually been proven.
Credit: Pooled is the work of Nehanth Narendrula. This page documents our hands-on testing and observations; it does not claim authorship of the Pooled project.
Test setup
Toucan · Windows PC
Ryzen 5 3400G desktop with AMD Radeon Vega 11 graphics. Used as the first browser peer.
Sparrow · iPhone
Used as a second device to investigate joining the same peer session from a mobile browser.
Browser connection
The local development/localhost route was not the successful route. The working resolution was to open the hosted Pooled website over HTTPS (pooled.run) on both devices. Using that live website, the Windows PC and iPhone successfully paired in the same Pooled session.
What we observed
- Localhost is device-specific. Opening
localhoston the iPhone points to the iPhone itself, not the Windows PC hosting the local page. - LAN addressing helped with access. We switched to the PC’s local network address (192.168.0.155) so the phone could attempt to reach the PC-hosted page while on the same network.
- The hosted HTTPS website resolved the pairing problem. After moving away from the localhost approach and using the live Pooled website over HTTPS on both devices, the PC and iPhone successfully paired in the same session.
- The interface displayed two devices and 4.5 GB of combined allocated capacity (4 GB on the PC and 0.5 GB on the iPhone) during the test.
Current conclusion
Successful result: We opened the hosted Pooled website over HTTPS on the Windows PC and iPhone, shared the invite, and both devices successfully paired in the same session. This was the working resolution; we did not need to make a separate test page.
However, we have not yet verified that model layers or inference work were actually distributed between the PC and iPhone. Pairing confirms that the devices joined the session, not that both devices processed parts of a model.
To call the experiment successful, the next test needs to demonstrate a real inference request, confirm that work is distributed between the peers, and capture evidence such as device-level activity, logs or a reproducible output. Until then, this remains a connectivity and capacity-allocation experiment.
Next steps
- Re-test peer connectivity on a stable network and document the exact browser/device combination.
- Check whether both peers become active for an actual inference request.
- Capture logs or other evidence showing which device processes which part of the workload.
- Record performance, reliability and any mobile-browser limitations before drawing conclusions.
Project references
For the upstream implementation and live project, see the original Pooled resources: