Big fan of Handy as well. I often mix languages (german/english) and Apple onboard dictation is not working well in these cases. Having the ability to switch models so far has proven to be helpful. I guess Handy should implement the new native Apple APIs though.
Whats definitely missing: a solid (non Mistral) GDPR compliant coding plan / subscription. All offerings are either US or China based. With the newest open weights models this became really interesting imo.
German here. Have a kid in elementary school and one in middle school. No phones allowed whatsoever. But to be fair: every school in Germany can decide that for themselves. But when we were choosing schools, all schools had similar rulesets. Some event prohibited smart watches.
Czechia had per school rules as well (my kids school bans them in school premises, which leads to groups of kids starting at phones in front of the school, sad sight), but as discussed yesterday by minister of education it's clearly not effective and still huge part of kids use them during school breaks despite more than 90% school officially banning them.
Czechia was one of the, if not the last country in EU without nationwide smartphone regulation
Btw I can't imagine putting my kids in education system in country where you don't have home schooling alternative to state indoctrination in case you need it. And German 2015 immigration crisis and green deal clearly show us your leaders can't be trusted at all.
I recently attended a agentic SWE workshop and the starter project was this, whispr style, local voice dictation app. Took everybody around 30mins. tbh: i was kinda impressed.
I just don't have the bandwidth to run another project, maintaining Handy is hard enough on it's own, especially for free!
I didn't just dismiss for no reason, I am a human! I have needs and I can't just sleeplessly stay in front of the computer putting out code. If I had more time I would, but alas.
Someone could easily vibe code an iOS version in a few hours. I could do the same but I do not have time to support it.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
I was using Twilio, and as far as I'm aware they handle any echos that may arise. I'm actually not sure where in the telephony stack this is handled, but I didn't see any issues or have to solve this problem myself luckily.
Mirrors my experience as well. Especially the pro-activeness in tool calling sticks out. It goes web searching to augment knowledge gaps on its own way more often.
