Alexandre Bantz

@performat
93 Followers
97 Following
342 Posts

I make Bloom, the note-taking app for the rest of us.

Expect some French too. 🌸

Bloom: Quick Noteshttps://apps.apple.com/us/app/bloom-quick-notes/id6443783029
One of my main goals for Indigo was working out how to show threads and replies without looking cluttered and I’m so happy with what we achieved

Here's a strange situation:

thousands of #Rust developers use #bacon, #broot, #dysk, or #lazy-regex every single day — tools I wrote, maintain, and improve for free.

Their companies, though? None of them want to hire their author.

If you use my tools at work and your company does #Rust, I'd really appreciate a hand landing a job or freelance mission. A boost goes a long way. 🙏🦀

https://dystroy.org

dystroy

dystroy - Rust consulting

Oh cool! Apple went back to the original "App" placeholder icon where its a pencil, brush, and ruler for the Developer app. :)

@ian_greig thank you for the heads up!

Let me get the full picture and come back to you.

@ian_greig Bonjour Ian! Thank you for your feedback and for supporting Bloom!

This initial version indeed uses Apple’s provided dictation feature.

I’ll explore switching to a better provider. I’ll reach out soon again on this.

@carnage4life genuinely curious:

can 2. be - even partly - delegated to LLMs or does it necessarily require human involvement?

Everything is for the best in this best of possible worlds, right? Right?

https://z1nz0l1n.com/26w19/

26W19. Best of all possible worlds

I was leafing through a collection of George Orwell’s essays when i stumbled upon this gem from “Looking back on the Spanish War”: I know it is the fashion to say that most of recorded history is lies anyway. I am willing to believe that history is for the

Z1NZ0L1N

@lickability I don’t think agentic automation will eat software.

I think good UX still has beautiful days ahead of itself.

@lickability All this to say that I do believe a lot of problems are indeed begging for agentic automation. And those are probably tasks where approximation is tolerated, like summaries and synthesis for instance.

But these remain mere previews for when the task does not justify that the user is going to dig into the actual data, or to orient their research before actually doing so.

These still cannot be trusted.

@lickability The art of prompting is dying because they have been getting better at _inferring_ what we mean in lapidary prompts, but I wouldn’t say I can trust the tool more as it evolves.

It still lacks taste and judgement. It remains non-deterministic.