Many of us oldies who started working on the web years before IE 6 actually like Tailwind. We all have our preferences. But I know multiple 50+ year olds who have been doing this work since CSS was barely a proposal who now use Tailwind.
Hah, yeah, there's always anecdotes. I stopped doing frontend a decade or more ago (and even then it had been a smaller and smaller part of my day). But I see the appeal of it. I started front end when we had to buy testing desktops that were beefier so they could run multiple VMware VMs, one with IE3, 4, 5, 5.5.
I remember the delight that our designers had when Javascript came out and my buddy showed that you could do some magic on images and form elements and have an actual checkbox with a check in it, not just a filled or empty box or circle. Or of the dev who thought he'd impress a girl on IRC by updating a prominent site's homepage to have a "Hi Sara" underneath the banner because he could just ftp to prod from his desktop.
Use a harness like OMP that lets you choose which model does which things. My main model is GLM 5.2, it handles planning and anything I dont have covered by other models. Tasks from todos and in sub agents are done by deepseek, I have different models for the git work like add/commit/push (that goes through cheap Minimax M3), and so on...
This way the expensive/strong model only handles the architecture and orchestration tasks. The cheaper models handle everything else and the strong one knows how to tell them what to do in enough detail to get good work out of them.
I've done a little bit in this space to try and see what works, and maybe it is different per language/framework but found the use case seems best for largely mechanical code changes, eg small direction, lots of simple changes. This sounds good until you realize that IDEs generally have built in functionality to do these tasks waaay faster, cheaper and more accurately.
What exact specs do you have? It might be because it's the 256 GB version. afaik, those versions have much slower memory bandwidth than the 512 GB models
My friend tried it on an M4 MacBook Pro and got 25–27 tok/s
This is correct, the 256gb is substantially slower as uses fewer physical memory chips - less ability to read/write in parallel. The 512gb or larger models have substantially higher read/write rates, and typically performs 50-100 percent faster in benchmarks than the 256.
Was a primary factor in me buying a 512gb M4 Mac Mini, even though I planned to use large external SSD - I wanted faster spec boot volume.
I do this in OMP, a fork of Pi. It lets you set different models for different tasks. So with an API that has many different companies models I can set the Plan model to the best one, right now I am using GLM 5.2 for that, it plans really well. I have Vision set to Kimi 2.7 Code (cheaper and vision is just fine). Minimax M3 is set to the Advisor role (double checks work). Deepseek v4 Flash is set for the Task role. And MiMo 2.5 pro is set as default.
With this setup GLM handles planning and managing my AGENTS.md, and orchestrating subagents for tasks from the plan/todo GLM created. The tasks themselves are handed off to Deepseek v4 flash to implement with strong instructions and examples for each agent. Minimax M3 reviews the output as the Advisor and recommends changes, catches bugs, and whatnot, subagents can be re-run with that information.
Overall I am saving a lot using some of these smaller models. But with this setup I am getting great results.
Stock OMP. When you add a provider and then /model you can choose a model and choose what roles it will take. Do that for each role it has.
Then I use /plan when I need to be planning and not writing to any files. Take the advice the UI gives you where it tells you to add the word orchestrate into your prompts when you want to make sure it uses its todo/tasks and sub-agents.
It would be nice to have a sample of the audio quality and voice(s) it uses on the website so we know what it will sound like.
--
Edit:
I installed it, ran it and got the first time wizard, granted permissions and hit continue and it just exits without any other message or screen. It isn't in the menu bar. I run it again and get the same. It says the permissions are granted already the second time though.
I like the interface on the website a lot, so I would love to use this. Thoughts?
On it! Pushed out a fix for something else earlier and didn’t go through a clean install to test. Should have a fix shortly. Just getting off a plane though. Will follow up when I have it nailed down.
Okay, 0.1.9 is out now and should fix the issue... I also added a way to report crashes, so IF it still gives you issues, let me know and please report the crash
Tried it out - tested on a few bits of text and it reads 1 sentence then goes non-responsive and pegs a cpu core to 100%. It doesn't crash so I don't have opportunity to report. I have to force quit the app manually.
Found the issue, published a new build, added a few features, and tested on a few devices now that I'm back home. Should be fully operational for you now!
Can you paste your system specs here for me? It's running for me just fine and on a few other laptops here, but I am curious if there's something on your laptop that might be giving issues... It does require Mac w/ Apple M1+. Happy to debug and get it working for you!
Okay, 0.1.9 is out now and should fix the issue... I also added a way to report crashes, so IF it still gives you issues, let me know and please report the crash
I had to click Skip to get past the intro screens, then the app comes up. I went to settings and pasted in my license, clicking activate says it's not valid. It is the key on my polar.sh account and I copy/pasted it so I know it's correct. Then it crashed.
Oh also, on the website, the first preview in the hero does give a real synthesized example I pulled using the app! Its not clear that the other screenshots are not interactive
Sure and Mozilla is arguably the cautionary tale here. They also started as a non-profit taking donations. AOL seeded them with $2M, Red Hat and Sun pitched in too. Within a year they had the Google search deal. By 2006, ~92% of revenue came from Google.
On Tahoe my Time Machine was broken after the update. My backup target is on a QNAP NAS. I just had to set it up from scratch again and it worked. But it did cost me a few files I was trying to recover. So I feel this.
