6 Comments

Awesome idea! I’m so in doing this, or trying to.

I wasn’t aware of Bland and tried it today. Wow!

Expand full comment
author

Thanks Nico! I'm hoping to post an update on Alfred sometime this month:)

Expand full comment

I am not sure how you are planning to approach this. I would love to connect my calendar/schedule and some basic task and focus list first, then have Alfred call me up and keep me on track on both.

Even if at first it would only be retrieving from the calendar and todo list, and not being able to modify it or add items, it would be a good start for an MVP.

How about we do some live hackathon on this? Could stream it or host a small meeting/webinar.

Expand full comment
author

yeah I think at first I'll just connect to my calendar to make the stuff I'm already doing available (retrieve existing calendar events + auto-book todos as calendar events from Siri via my apple watch).

I love the idea of doing it via livestream let's do it! I'm knee deep in another project rn (will post about it sometime this week) and then I go on a long overdue holiday but will be back 21st Sep and then I'm all in!

Expand full comment

Amazing post! Super intrigued on the costs to run the entire alftred at the end? between licences, storage and api calls.

Its crazy I've been picking up coding again thanks to AI :D its been 10 years since i last coded

Expand full comment
author

I'd also love to know :D

For prototyping I'll just use off the shelf stuff, but I'm already thinking that the highest possible cost would be LLMs and multimodal stuff. I can use open source and/or fine-tuned models for each. If I have the use cases nailed down, I should be able to go smaller in LLM size, saving tons. Claude 3.5 and GPT-4o are like an Abrams tank. Incredibly powerful and capable but there are also other ways to cut down a tree that don't cost that much :D

Expand full comment