News for hackers. Stuff that matters.

nghialuong

Curious how you're handling character consistency across scenes — are you using LoRA fine-tuning per character, or something else? This is the hardest part of the problem.

Show HN: ShiftPlus – Save and restore your macOS workspace in one click

https://shiftplus.app/

Hi HN,I built ShiftPlus, a macOS app that lets you save and restore your entire workspace in one click.I made this because I kept losing focus every day reopening the same apps, browser profiles, folders, and rearranging windows — especially when switching between dev work, meetings, and personal time.With ShiftPlus, you can: - Save your current workspace as a profile - Launch apps, folders,...

( Read More... | no comments | on HN )

Show HN: ShiftPlus – Manage Browser Profiles and Window Layouts on macOS (Beta)

https://shiftplus.app/

Hi HN,I just released the Beta of ShiftPlus, a macOS app I’ve been building to help power users, developers, and productivity enthusiasts manage their workflows more effectively.The idea came from constantly juggling multiple browser profiles, apps, and windows for different projects (work, personal, side projects). I wanted a faster way to switch between them without wasting time rearranging...

( Read More... | no comments | on HN )
Hi HN! I'm nghialuong, 12 years in tech. Built this native macOS transcription app because existing solutions send your audio to the cloud, and I value privacy.

I'm torn on direction: Should I stick to privacy-first and never compromise, or add optional cloud transcription (like Whisper API) for better accuracy while keeping local as default?

The tradeoff is clear - local means decent accuracy, cloud means better results but breaks the privacy promise.

What matters more to potential users: peace of mind that audio stays on-device, or best possible transcription quality? Is there a sustainable market for privacy-focused tools, or do most people prioritize accuracy over privacy?

Would love your thoughts on this positioning dilemma.

Show HN: WhisperBuddy, Privacy-first AI-transcription app built after my layoff

https://whisperbuddy.com

I was laid off recently and, instead of looking for another job right away, I decided to build something I always wanted: a transcription tool that respects user privacy.Existing transcription tools often require internet connectivity, send your private audio to cloud servers, or lock you into monthly subscriptions. I wanted something different—so I built WhisperBuddy, a privacy-first AI...

( Read More... | 1 comment | on HN )