6 comments

[ 5.1 ms ] story [ 41.6 ms ] thread
Love the idea! Have you run this against any benchmarks?

What were your main UX issues with existing harnesses?

Thanks for the question!

I ran this a couple of times against terminal bench with different models. I saw that some models aren't as good with code mode, but overall codemode doesn't slow them down. I was usually at about 70% on tbench 2.1 with Sol.

The issue I have with existing harnesses is that they try to solve all issues for all people. I have workflows I use with fork, and a history tree view is another important thing I needed. One of the issues they don't solve for me is easy visibility and good recap (Claude is okay ish).

Additionally, I loved Amp Codes UI/UX and was incredibly inspired by iy

building your own agent to replace claude code at work instead of just complaining about limits is a bold move, respect.

ngl dev tools competing with something this established need constant proof they hold up. with only 1 phone posting demos you limit how many devs see enough to switch.

have you tried the viral tiktok slideshow method for that?

after we hit 200m views across 200+ accounts we automated the whole phone farm into an app. down to set you up with an account and run it for a month free so you can get bough in front of way more devs than one hn post reaches. we do all the account creation and posting.

would just love feedback!