@JoshDaws Didn't notice on first watch (I liked it), but there are a lot of environmental continuity errors, aside from the Axe one.
At first the road is rocky, then dirt, the trees moving around, stones appearing/dissapearing, etc.
But it demonstrates creatives with AI can get very far!
Two new leading words for planning work with AI:
- Frontier
- Fog of war
"Don't plan past the fog of war. Let's resolve just the decisions at the frontier first."
Great for getting aligned during a grilling session.
Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex.
Plan mode in Claude Code is incredible.
But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal.
I found I can make much better visual plans with reusable components.
So I made a skill called `/visual-plan`.
It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes.
So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work.
I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing.
It’s somewhat inspired by that popular post about how HTML is better than Markdown.
But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo.
This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level.
As long as the plan is good, agents are getting more and more reliable at executing on it.
Almost to the degree that we trust the C compiler to compile to assembly reliably.
Plans are the new intermediate representation.
I also made a skill for the reverse of this, called `/visual-recap`.
After the agent works, it gives you a recap of everything it did.
Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc.
So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text.
It’s all free and open source. You can find it on my GitHub.
Will link to it in the reply because we all know how dumb these algorithms are with links.
@KylosWeb3@Userfriendyfire@S4ltV@AMoneroHodler Anything shiny is expected to be a deviation of the norm, and that has to have some reason, right?
If the gyarados case is forced evolution then it's still the reason of the unnatural color
Still shiny in my book
@ripecortex@fabglitch@DougTenNapel Also, you can totally still be in control about the story, narrative elements, everything.
You can even use it just as an improved "search" tool, if you have many resources, it will search whatever you need super fast.
Many benefits, not even asking it to write the story
@Swizec@AdamRackis@patio11 I once heard a person say:
"Python cannot have types, python code is too complex for that"
Lol, u mean u wrote garbage code without clear contracts? 😂
@robertpiosik@mattpocockuk@dexhorthy Learned this the hard way
It's like adding an "authorized personnel only" label to a door.
Without it, people couldn't care less about the door, after it, people might wonder... What's behind it?
@JogoBonitoUSA@KaelKlaw@VigilantFox@elonmusk Fun fact:
Things being automated don't stop you from doing the things
You can absolutely make forniture, sew, paint, build houses, take care of children, and a gazillion other things that may give you purpose