Learning to work with different AI models feels like learning to work with different teammates. Everyone can have the same hard skills, but how you communicate and do your best work is different.
It's been fun evolving Flyway not only for existing users, but also for something I need for projects at Be01. This one sorta hits both of those notes.
If you're interested in trying out the early version while we're wrapping up development, lmk. Shooting to get it live soon at https://t.co/RZ2orLwVBq
Introducing Storybook in @GeminiApp today! Now you can create personalized, illustrated storybooks with read-aloud narration in 2 simple steps. It's free and available globally right now.
Here's how to make yours + a famous story from our house about "Teddy" …
Wrote a longer piece about what I think might be a new superpower everyone should develop if you're working with AI.
Curious about your take & would love to swap notes!
https://t.co/Lwi1ku0hHu
Everything has tradeoffs,
but one thing I do appreciate about all things vibe-* these days is it's turning more people into doers rather than just talkers.
Something I do differently with AI during research:
I actually ask it NOT to synthesize.
Instead, I ask it to pull exact user quotes (word for word) and group them together. Makes pattern recognition way easier for me personally.
Less worry about hallucination + reading customer quotes directly just makes validating ideas feel more real.
I want a sassier AI in my IDE.
One that pushes back at me more. Maybe say 'Are you sure?' or 'This could be cleaner.' once more even if I don't ask. Blind agreement is going to be a bug, not a feature.