Practical AI Creating a private AI assistant in Thunderbird
168 snips
Sep 23, 2025 Chris Aquino, a software engineer at Thunderbird, shares insights on developing a privacy-centric AI executive assistant. He discusses the journey from relying on large models to a modular approach, splitting tasks among smaller models. Key topics include the challenges of local versus remote processing, the importance of privacy in AI features, and how user feedback shapes future developments. With a focus on encrypted inference and efficient workflows, Chris envisions a new era for email management that balances functionality and user privacy.
AI Snips
Chapters
Books
Transcript
Episode notes
From Web Dev To Thunderbird
- Chris Aquino described his path from web developer to Thunderbird after layoffs and applying to Mozilla.
- He joined to build experimental products under director Ryan Sipes and started working on Thunderbird-related projects.
Thunderbird's Privacy-First Ethos
- Thunderbird is a 20+ year open source desktop email client spun out to continue maintenance and development.
- It emphasizes user control, no ads, and offline access to email as core privacy-focused differentiators.
Tradeoffs: Time Savings Vs Privacy
- AI features in email commonly include summarization and autocomplete, which save time but can alter tone and feel intrusive.
- Thunderbird users value privacy and want explicit opt-in controls rather than always-on AI reading their mail.
