writing at https://hank.bond slowly working to those skills
currently my fun project is https://github.com/hank-bond/uix which is "visual agent harness" that uses rendered html to communicate between agent <-> human
I have not set up Hister yet but it's on my list to try out. How would I do something like host it on my Unraid box but have it index/persist my local MacBook browsing history?
Very well written article. Had a natural feel to it that was engaging and relaxing. The broader point of just having complete abandon for natural resources when manufacturing was certainly of the era (not that it has directionally changed much).
As a new TypeScript user these are concepts that have greatly helped me simplify my code and improve reliability discrete of testing. Many LLMs guide in this direction if you loosely ask them, but having a concise post like this with the what and the why is fantastic as reference material. The suggestion to use Separation and a Linter rule is something I'm going to immediately look into for my current project. Great post!
do you propose its maybe closer to the idea that you can regain strength faster after having lost it (in the context of bodybuilding and extended time off)? Gaining something from scratch requires much effort and experimentation, regaining it less so?
People also build the same things if they have the same needs. That doesn't mean creativity is dead. My life as a software engineer is not that unique of others. This isn't really something to lament. There's nothing wrong with exploring similar ideas.
Wow this is very similar to the direction im taking with my new project https://github.com/hank-bond/uix (warning the code base is certainly not messy but the application is barely usable for anything as of this post).
Here the goal is to be a self-assembling harness (akin to pi) but focusing on duplex human-agent interactivity over rendered HTML "apps". To start, it's focused more on the "please review this PR and then generate a one-page report" with the ability to write comments in the actual report that automatically get sent back to the agent. The end goal is closer to offering a substrate for less technical people to be able to build personal applications like
- an interactive wiki maintainer: chat with the agent about an article, pull out sections, append/create concepts in the wiki with the new info
- agent code harness: agent tabs to the left, chat in middle, code diffs on the right (like the superset/commander class of apps)
Anyway, I'm really into the "self assembling" class of software where everything is basically just an SDK + Agent. I think we might actually be ushering in a new era of "personal computing" in that it's less friction than ever to personalize your setup to your whims. Anyway, thats the goal I'm reaching for.
It seems many others are coalescing on this idea at the same time, so it must just be in the aether.
This was well put. Some things I just want done because I need to use them now. Some things I want to take my time because it's an opportunity for me to expand my knowledge graph and/or something I want to be durable (so it can't be slopped up).
Sometimes one turns into the other. For instance I started building an agent based wiki generator fully vibed. I just wanted to test out if it was possible to mostly automate information extraction and conceptualization. Tried three times before realizing that the path I was attempting to travel was just not going to get me the results I wanted (fully automated meant I was not reflected in the wiki). So I finally started more carefully vibing out an application that implemented some of what I learned would be useful, at the same time I was developing a structurally similar app for local dev harnessing. Realizing that they had a lot in common, I started yak shaving and focused on building a framework that would make it much easier to whip up these types of agent based apps. This is the thing I started from the ground up building much more intentionally and thoroughly.
AI is used all throughout, but the amount of leash differed from holding without looking to wrapped around my wrist twice I'm basically holding the collar at this point.
This was a very well written piece that contains just the right amount of context to understand how to place the concept, an easily digestible length, and a sort of to the point whimsy that's not overbearing. Saving this as a reference for writing style!
I played few on itch.io but it seems like most of these are more interactive poems/stories than games? Does anyone have any recs of some bitsies with more traditional game elements?
Is the implication of this that damage was caused because existing tests were not version controlled, or that new tests were not yet committed? I'm confused as to what damage this was intended (or in actuality) caused?
I don't know if this will bring you any comfort, but I think
> And you learn in your career that it's a bad idea to care about the code, especially in a business context, which one's career is very much trapped in the business context.
It's always been this case -- well before LLMs hard pivoted the field. You (theoretically) get paid to create net business value, you don't really get paid "to code". If the product you are creating is code, then yes the priority of code quality can be much higher. Especially in higher IC roles like Staff+, coding is just one of the ways to add that value.
At work I just have to solve the problem at hand with the minimal amount of effort to reach the first acceptable solution. After work while at play, I can explore 10 versions of something at my leisure, just to learn if I want. I can focus on working the thing until it's polished and elegant, because I decide what the priorities are. I can be as selfish as I want.
It's common in art circles that you have a series that you can churn out for money, and you have ideas you explore just for you (that often are far less appealing to non-artists). Pixar used to have a tick-tock cycle like this, "one for them, one for us". They would alternate a sequel bc it would make money and new IP because it would keep the studio fresh.
I don't think accepting this should be depressing. A good life is all about finding balance so that you can sustain it for the long haul!
It's easy to start learning on, or prototype with, and then sometimes momentum just keeps it going. Also it may not really be the best at anything, but it's "pretty good" at just about everything. It's kind of like vanilla ice cream.
Packaging can be irritating although uv takes the sting out a bit.
You are right that outside of verbosity, once you get used to the syntax of a language, the value of one over the other kind of fades.
You know what, you are right on the money with that. I think if you expand to include functional/smoke/e2e tests, that covers pretty much everything documentation is supposed to be.
Just by running them you can measure if they are in or out of sync with the code (well, if they were written correctly).
currently my fun project is https://github.com/hank-bond/uix which is "visual agent harness" that uses rendered html to communicate between agent <-> human