DigestAI news desk

Cut through the AI noise.

Hardware & Compute5 min read

I built an AI Tamagotchi before Meta could

The author bought a $50 Waveshare ESP32‑S3 1.75‑inch touchscreen pendant, which Meta lists as a “Muse Gadget” kit. After plugging it into a PC and pairing it with the Muse phone app, the device initially treated speech as transcription, responded slowly, and only showed a few words on screen.

1 source

Key points

  • The author bought a $50 Waveshare ESP32‑S3 1.75‑inch touchscreen pendant as a DIY Muse Gadget.
  • Claude was used to add conversation history, ElevenLabs voice, camera control, avatars and a Tamagotchi minigame in minutes.
  • Meta’s Muse Charm currently offers only a single avatar, limited smart‑home discovery, and no out‑of‑the‑box voice output.

The changes took minutes, but the author notes no coding experience and raises security concerns after a reported address leak.

The hack shows the Muse platform can be extended far beyond its limited out‑of‑the‑box features, yet the author wonders whether the official Muse Charm will be as freely programmable and if non‑technical users would prefer a development kit over a dedicated pendant.

Model page: Muse →

The story so far

4 episodes →
  1. I built an AI Tamagotchi before Meta couldthis story
Full story from The Verge AI · by Sean HollisterOpen source ↗

I built an AI Tamagotchi before Meta could

The Verge AI · 31 October 2026

Loading the full article…

This text was published by The Verge AI and written by Sean Hollister. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
MetaElevenLabsWaveshareClaudeMuseMark ZuckerbergAnant NarayananJeremy Payne

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Hardware & Compute

All →

Related stories