Ok fam
What are we going to do about github actions
Like for real
Why are we doing this to ourselves
There are a LOT of dog shit things about the NFL app and NFL plus... But their pre-game previews are soo excellent
Ty retweeted
I have layered disdain, hatred, sympathy and empathy for this anguish but at the end of the day you are all beautiful, delicate souls and so I will say this:
the loss of specialized expert status is not the root of your suffering, you fear becoming completely unneeded. you fear it on a primal level, because nearly all humans fear it, because in the dim villages and cities of our evolutionary youth to be unneeded was to be one step away from obliteration.
start by seeing what truly scratches at the back of your mind, then consider what must be done with that feeling. my darling child, you do not need to be afraid of the dark anymore.
Logged into my jev console expecting to have used idk, maybe like 5 cents in credits. Off by an order of magnitude
Every email I get that isn't access to Jev is just a waste of both of our times. Pat, id like to solve the puzzle
I think most of this slop/not slop moral crisis is a result of many people never having to do any actual research in their lives. The prolifefation of bullshit just means you need to work on your bullshit detector. The trick is to learn where on the ROC curve you wanna be
And just like that what's old is new again
Society is so funny
Given that agents still need high level supervision. And given that the human review of code is a bottleneck. And given that the models have gotten good enough that strict deterministic harnesses are suboptimal.
Then how should we supervise their output.
My current solution is to use an interrogation tool coupled with an agent. The tool displays the structure of the system in a UML-like diagram, color coded with crap and mutation scores. The diagram is dynamic, allowing the user to click on element and drill down through the architecture -- all the way to code.
The user can detect structures that need improvement and tell the associated agent to make the appropriate changes. These changes can range from high level architectural changes, to the lowest level code refactorings. The associated agent will make those changes and cause them to be redisplayed.
The tool I'm using is custom made for me, but you can point an agent at it and use it as a template to build your own custom tool.
It's a work in progress, so don't be surprised if it changes a lot over the next few weeks. But then you probably won't care because by then you'll be deep in customizing it for yourself. And anyway, you can always point an agent back at mine, or someone else's, and integrate improvements into your own.
github.com/unclebob/uml-view….
