This is really nice. I'm able to read Hiragana and Katakana fully after about 4-6 weeks now but then I'm hit with the reality of how many Kanji I have to learn still everytime I want to read something in real life lol
I used to do it but now I only review code organization and structure.
Mostly I define the product behavior I want and discuss the technical implementation beforehand.
Once that's in a spec I let it build in my durable implementation engine. Automated verification, review rounds from different agent types across different models, issues triaged into meaningful clusters and flagged for false positives before finally being fixed.
That loops until the code is up to spec.
There is no special secret, LLMs need repetition and multiple passes.
They'll one shot bigger and bigger things in their default harnesses but they'll be filled with issues no matter what.
"be able" implying capability rather than time constraints and opportunity cost which is what most people on here refer to when they mention something cool they're doing with LLMs that they weren't doing before.
I've been looking at offloading local work from my MacBook Pro (M1 Pro / 32 GB) specifically because I've been working with a lot of Android apps and emulation is killing me on top of everything else that I'm running.
Got a bunch of Daytona credits which are close to useless given their restrictions until you hit tier 3.
You seem like you're actually slightly cheaper than https://boat.dev/ but with less storage? That's the closest to your pricing unless I'm mistaken. Any other insight as to differences between you two?
Also I'll add you to a list I've been maintaining of sandbox providers, congrats on the launch!
I find the whole category of "added value" STT apps funny at this point.
Built my own in a day that blows them out of the water. You can quite literally pick any sufficiently good local model or API provider and combine it with Cerebras for cheap and very fast AI post processing and formatting.
If you want the best accuracy, then this is not true. Combining models will beat any single model. There's also a lot of work that goes into optimizing dictionary words and screen context, and knowing which ones to, to add to model context.
reply