thiagoperes

it feels this will keep happening specifically to Europe for three reasons: a) most countries took an anti-AI approach b) they reject frontier models in favor or "Sovereign" solutions c) they're replacing software with weaker/more vulnerable options

public servant engineers are token poor and will be out of the latest defense tools

It's free as in: no logins, no servers, everything is local and using open formats, export anytime. Syncing is paid, but if it's a huge detractor I can get you a promo code for a year's worth, just email hi at peres dot pro

I wanted to make an app that the world doesn't need another of, because that's my usual day-to-day.

This is another game, my focus is to sweat the details and try new approaches/new tech. I also think most editors don't really do a good job so wanted to build something for myself.

Lastly I wanted to build something silly, there isn't a lot of software that looks like Winamp, this is my small ode to those days.

Fair feedback and looks like a lot of folks agree. I've removed some content that felt off. What else gives you the vibe coded vibes? I actually spent some time polishing animations and other things to feel like a nice page lol

Thanks for these. I'll look into it! You can message hi [at] peres.pro with any feedback or report. There's a power user group as well if you'd like to try the betas

Funnily enough, this is the only sentence written by myself. Other parts of the post were written with the help of AI.

Maybe I spent so much time using AI that I started to write like them?

Someone has to do it

There's no revenue model, no clear goal. This app is a creative outlet and a sandbox to try ideas. I added an in-app purchase as a test to see if anyone cares, it would motivate me to keep working on it.

Without the constraints of a usual project, I feel I'll actually work on it for a much longer time.

I didn't add any story or personal background because I didn't think anyone would care, but good idea! In the meantime, you can follow along on x: @thiago_peres

We run a lot of varied, tiny, simple workflows that were previously running on 5.4-nano and mini. We transitioned them to 5.6 and noticed exactly this range of improvement across the board. In a few cases, we had improvements in classification.

I think a lot of people miss that for many companies, a model upgrade like this is basically a one liner.

Even if you have an amazing model router architecture (which we do for our golden flows), it’s just not worth it. Not to mention reliability and so on

People usually think of "making it" as a single point in time that's binary. Granted, there's some truth to that: most people will feel fully comfortable with a few millions in their bank account.

But in reality, success can be savored a lot more pleasantly if you allow yourself to be conscientious of milestones and include having a great process of getting there as the definition of success.

I've met so many people (myself included) that burned themselves by thinking they will spend only a few years grinding to reach a certain milestone, and get frustrated when the narrow definition of success they've created for themselves isn't met.

I've also met a few others that have realized the above, usually with burnout then self-discovery, many which also "made it" by the standard definition, but have a strong sense of fulfillment.

Naturally the question is how. For myself, what worked is a mix of taking more risks (becoming a founder at 35+), experimentation and using various techniques (therapy, meditation, the usual suspects) to find what can drive me to work hard but with purpose or joy.

It's poetically beautiful that the tool was very very clearly built mostly if not entirely using AI