1,233 karma · joined December 4, 2011
And so lately, pretty much the only reason I have VSCode open anymore is to view the diffs of what my agents are working on.
I wanted just a simple, lightweight, fast and KEYBOARD powered git diff viewer.
Suprisingly there were not many options, so I just kept using VSCode.
Eventually, I decided to just build it using GPUI (amazing) and have been pretty happy with it so far. Been using it a couple weeks and has actually replaced VScode for me most of the time.
So thought i'd share it here in case anyone else is looking for something similar.
It's open source as well, so feel free to just run it yourself or make a PR or critique my (agents) rust code: https://github.com/hitSlop/Diffy
Theres still some features I want to add but for the most part I really just want it to be a simple to use and fast git diff viewer.
If you are on Windows/Linux i'd love to know if it's working ok over there as I havn't really stress tested those.
Saw it on HN a few weeks back
For anyone else that's been thinking a lot about Ted this year, I recommend this (weird) youtube series:
https://www.youtube.com/watch?v=pGpBQgZ5IsI&list=PLsfH1Ahi4S...
Have you looked into the semantics of their like StreamDB stuff ? Pretty interesting
Also there is this that was built on top of it. Sounds somewhat similar goal as yours but I could be off. Need to explore more https://ursula.tonbo.io/
You can still always get around them (at least my experience), but it just takes a lot of time
Since the first image models started coming out i've been testing each on making app store screenshots, hoping one would be able to handle it.
Finally, with OpenAIs gpt image 2, it was finally possible!
I made an open source library that gained some traction but not everyone had gpt image 2 API Keys (you need to be verified corp) so I decided to make it as a MCP that you can add to any agent.
It's very simple to use. When you are done coding it up, add the MCP and tell it to make screenshots. It will pull in reference image, screenshots and your theme and research the space then propose some ideas that you can approve/refine.
I also handle revisions and translations as well as app store copy.
Would love any feedback and if you run out of the free three screenshots but not ready to pay feel free to message the chat I can give you some more credits for feedback!
I've been trying every model since AI image gen came out to see if they could do them. Nothing was consistently good enough.
With gpt image 2, it's finally consistent enough to use to generate app store screenshots that look incredible (imo), hallelujah!
It's pretty cheap too, about 20 cents a screenshot. And i've been impressed with the quality!
If you use it please PR your examples if they turned out good, or leave a issue if the result wasn't very good - i'm still tweaking the prompts