I’m exploring agentic for creative coding / visual effects. Think touch designer but with a prompts graph. It compiles to native code (swift and metal).
The first version is available here and I’ll be releasing a v2 soon that will be open source:
I know how to build PCs but suck at picking parts, would you happen to have a recommended build or links to people who've done similar ones? Heck I'll click on an affiliate link to support the author of the build :-)
Same here for the flash card app! I literally built this for myself after reading about spaced repetition from this amazing web comic: https://ncase.me/remember/
Then… I wanted to apply this to (beginner level) language learning. And yep you have to be disciplined to go through the cards daily, but it works.
My app is 100% free so my trick was to have users write what they need, the app generates a prompt to give to any AI provider, which in turn gives you back a JSON that will be converted into a deck.
Nothing truly ground breaking, but again it works for beginner level concepts :-)
I’ve worked in VR for a long time (including visionPro) and my eyesight definitely got worse. The most ironic thing to me is how iPhone has this screen distance warning telling you to move the screen further from your face while Vision Pro is literally an iPhone strapped to your face.
Maybe not photoshop but I’m building in the live VFX (visual effects) space, for example think touch designer or Houdini (but simpler).
My first project was an “old school” node editor done almost entirely with agentic coding. I slapped an MCP on it to see if the agents could make cool stuff and it was mostly hit or miss, but nothing too mind blowing.
Blog post about it: https://sxp.studio/blog/subjective-building-a-native-vfx-edi...
My second take on this is to channel coding agents into “prompt nodes” coupled with some agent orchestration. This helps define clear data flows and API contracts for each node + overall graph. This strategy works better since we’re constraining the problem space and overall getting better results when combined (and it also plays nice with context window limitations).
The current demo is a bit slow and basic but it’s looking promising!
https://sxp.studio/apps/subjectivezero
For the past 2.5~3 months I've been working on a 2D/3D VFX (visual effects) editor dedicated to mac and iPhone/iPad, it was on my never ending list of fun projects to build and a perfect excuse to learn agentic coding on a domain of expertise (written in Swift/SwiftUI and Metal).
Honestly not a bad theory. There’s definitely a huge disparity between actual productivity gained by using agentic coding done somewhat properly… and a non-stop wave of vibe coded work causing outages and churn. Pre-Covid hiring coupled with the high enterprise pricing for AI plans, it would make sense.
This is why I'm building free "spite apps" in homage to Larry David's spite stores [0]. The goal being to push back on enshitification of tech and dark patterns like mandatory subscriptions, ads and user data tracking.
As a solo indie-dev, writing free software (as in you don't need to pay anything) is fine, but I usually do not make the project (entirely) open source due to the added churn & maintenance.
In my experience, setting expectations early in my apps ("I'm a solo indie dev", "this is a free app", "you can reach out to me through email but don't expect super quick responses") helped reduce entitled users and - quite the opposite - people were super happy to get replies from me solving their problems.
That’s funny, I’ve actually used the same algorithm but with taxis in general, for having the same exact issue as the person in this article… but with a real driver.
(All of this assuming it’s safe to keep a door open!)
I’ve also started publishing a small collection of what I call “spite apps” (a reference to Larry David’s spite store when he makes his own coffee shop to go against mocha joe).
These apps are super simple in terms of privacy policy:
- we don’t track you (no telemetry)
- we don’t show you ads
- no account
- free with optional tip
Sure I don’t make much money with them but I feel like I’m pushing back on making humanity worse.
Same here. I was a fervent Claude code user at $200/mo until Opus4.7.
Freezing your IDE version is now a thing of the past, the new reality is that we can't expect agentic dev workflows to be consistent and I see too many people (including myself) getting burned by going the single-provider route.
On one hand I’m glad to finally see anthropic communicate on this but at this point all I have to say is… time to diversify?
Ironically, I’d be surprised if this wasn’t already the case before? I recall vividly employment contracts with meta in 201X with a clear mention that employees were giving up any sense of privacy while using meta provided devices or entering meta’s premises…
This is great! I found myself asking my AI agents to generate those icons every so often (esp. for websites), so thank you for taking the time to build this.
Quick question, are you also planning on supporting animations?
https://sxp.studio
~