Ex-academic turned Meta researcher on building browser-use agents for personal superintelligence
shuyanzh36 · x · 2026-09-19
shuyanzh36 shares that they left academia earlier this year to join Meta's personal superintelligence effort, focused on making models genuinely good at browser use.
Quoting EdwardSun0909: computer use has been a core agentic capability of Muse Spark since MS 1.1, with the model trained end-to-end to automatically decide between scripts and clicks to reduce latency. The author adds that a 2020 PhD statement-of-purpose dream—building a product their mom could use—has now come true.
Related event: Researcher Leaves Academia for Meta to Advance Browser-Use Agents(2 posts)→
More from coding & agent
- Grok Bots support webhooks, letting you trigger them from any platform — mattyp · 2026-09-19
- Agent installs mlx-whisper itself to transcribe video on macOS — vista8 · 2026-09-19
- LangChain browser agent demo: great at the Wikipedia game and finding cheap flights — colinmcnamara · 2026-09-19
- macOS 27 ships with mlx_whisper built in, letting agents transcribe video locally — vista8 · 2026-09-19
- Custom /jev command in OpenCode turns LLM rambling into instant yes/no answers — TheMoonMidas · 2026-09-19
- Dev pipelines Codex output to Muse via Google Drive, calls it insane — RachelVT42 · 2026-09-19