Can you share more about what makes them poor at coding? I haven't tried Google models, but I'm curious what issues you hit?

Yeah, having review/orchestration + subagents seems like the stndard way to optimize for cost/performnce.

Using OpenCode has been on the list to try. Logically, the value of a bundle from a larger company should technically beat out a smaller purveyor of open-weight models right? I also wonder how much OpenCode's token/sec throttling will impact my productivity?

I've heard that folks using using a mid-tier Anthropic model like Sonnet 5.5 easily run into limits. When I use GitHub Copilot (for work) with Anthropic models I can easily rack up quite a significant bill.

This is why I'm comparing value for the money.

While Google may not have the "best" models, what's the point if you hit a wall with Claude Code? The extra baseline quota with Anti-gravity could be worth it.

Wonder how much of this is social stigma related to an ever present mobile phone camera presence vs it's just healthier to not drink.

Anecdotally, you will get more mileage out of a Claude or ChatGPT plan than with a GitHub Copilot plan.

If you're worried about costs, you might try using subagents with a cheaper model or an open model like Kimi/GLM and use Claude/Codex as the orchestrator. This is very efficient.

I prefer using Handy(https://handy.computer) with these CLI coding agents. I prefer to decouple certain things from these AI companies.

Looks like it solves the speech to text piece but not text to speech? Neat tool either way.

I am looking for any examples of people fully working with their coding agent CLI via voice alone.

Others should check out Fluid Voice as it seems privacy focused with a bit more enhancements like custom dictionary.

So privacy focused that it sends telemetry, unlike handy.

The Product Manager on Facebook Dating already beat you to this...

I really like this approach. I wonder if it needs such complexity for the rendering. Could you have built this as a SSG template?

Hi, thanks! There is a lot of nuance on the rendered pages, I figured server-side React was the best choice - plus it's a technology I'm comfortable with and might also encourage contributions.

Would you be okay if I directed Claude to leverage your design and build a very simple Hugo template against it for my own personal use?

Why not, try it :)

Go get children's melatonin gummies and cut it in half. Problem solved.

I've been asking myself this question in the last year:

> Why do I want to make music?

I picked a basic DJ controller and a midi controller bundled with Ableton. I'm a novice, but I love listening to music and dissecting what makes a good performance. I crave that feeling of getting chills when I find something new that moves me in new ways. This set was a pretty recent example:

https://www.youtube.com/watch?v=gfF8jzBVWvM

That being said, the world is increasingly crowded with "good enough" music.

I resolved early on that I was never going to make a money doing this, which simplified things greatly. There's a primal part of our brain that craves adoration. I do wish for others to adore my music. Even if it's a handful of people. I do wish to perform publicly one day, even if it's at a park for passersby.

Mostly I just want something to move my brain in different ways. I want to create something beautiful.

>> That being said, the world is increasingly crowded with "good enough" music.

As I enter my mid-50s this is how I feel about the music I listen to. I have decades and decades of music I love for a variety of reasons. I don’t have time for “discovery” anymore. If I get introduced to a new band by someone I know or algorithmically, that’s great but I’m not going to spend hours trying to find the next great thing when I have so much I enjoy already.

I wonder if this brings back demand for IRC clients on mobile devices? ;-)