I don't dream or care about things I definitely can't do.
But there are still so many I can actually do that the opportunity cost of choosing any single one of them is infinite, and that leads to paralysis at worst and diluting your self while half-assing dozens of things at best.
Maybe one of them pays the bills, and even a nice house and a decent car. But it's just that, it is not what you really wanted to do, so you keep searching.
The "gift" of being a fast learner becomes a curse. In a few weeks you are an advanced beginner at almost anything. People marvel at how well you are doing, but you know you have just started and can now see how far you are from being any good. But to become good, you'd have to leave behind all the other things, and you can't pick. So you just start a new one for the quick dopamine hits and easy praise...
And then you are 50 and still don't know what you will do when you grow up.
Managers can barely direct me without shitting their pants. What saves them most of the time is my ability to say "No". Until LLMs can do that, which seems quite hard to do so far, good luck replacing me.
I always see these threads and think I'm not working on anything, but I just realised it's a lie, I'm exploring a couple of things right now, both heavily AI supported:
Simracing trainer.
I love simracing, I'm moderately competitive and want to improve, and I like to be efficient with my practice. So having access to and using a lot of telemetry, I noticed that the "turn a few laps, load telemetry, compare against reference lap, try again" is not as efficient as it could be.
Also a lot of my telemetry analysis is very rote and "rules based": Look at the biggest laptime delta jump against reference, try to determine the cause among a few usual suspects".
So I have started experimenting with a system that reads the iRacing telemetry in real time, and compares against the reference telemetry live, finding the biggest delta jumps, and trying to find the root cause of the time loss using an increasingly sophisticated GOFAI rule and pattern matching system. Then this report is fed to a cheap LLM call to be condensed into clear advice, and the result goes to the free Microsoft TTS API. So I get instant feedback of where I'm slow and maybe even why.
So far I fear it's mostly making me faster from all the test laps involved more than the advice itself, but when it clicks it does feel magical and really help.
But sometimes I feel like I'm just speedrunning the collapse of 70s AI, as it feels a bit too brittle and situational.
I also have added additional tools for tracking improvement across sessions, finding statistically problematic corners (where am I plain bad?, where am I inconsistent?) or even training my muscle memory by tracing fast driver brake traces using my pedal.
Yay compiler:
The other ongoing thing is a clean room reimplementation of Jon Blow's Jai. I've been curious about the language for years, but it's a closed beta and for some reason I've never felt about asking Jon to get into it. I'm not really a game dev so I wouldn't even know what to put in the request.
So now I have 100k+ lines of Rust that can compile a very significant subset of the publicly available Jai source code. I just used various LLMs to condense the public information about the language and come up with a dev plan and started chipping at it. Once I had something in a kind of working state I started with the Way to Jai big tutorial and make sure every example there compiles and works as intended, fixing errors or missing features one by one.
I mostly use Claude Code or Codex, but sometimes what I do is having them guide me into the new feature and doing the edits myself while they explain, so I get to know how things really work under the hood.
It's a silly pointless project, but for some reason I find very satisfying watching it compile the examples.
What has your career looked like? I'm interested because I've spent 20 years in applied research and I've only more recently realized the continual stress that I've felt for 20 years from trying (and mostly failing) to innovate in the "what to build" space.
Working for a salary on other people's ideas, LOL. Mostly incredibly boring ones. One interesting ones that fizzled due to too-low investment and too-safe management (odds are it would have fizzled anyway, of course, though I do think if that one had had the eyes of the right investors it probably could have done a "successful exit"—this was like 15 years ago though)
For me it has been just saying "yes" when I was offered a job and when that one was getting a bit annoying someone happened to offer me another and I said "yes" too. I have ended up a bit underemployed and underpaid, but life's comfortable and safe and I have ample time to stress over hobbies instead of work.
So comfortable that lately I have declined offers for interesting and much much better paid work, because I can no longer be bothered to take any risks or alter my lifestyle.
But sometimes I wish I could have been the guy managing to get 10k MMR using knowledge I've got in spades.
Well for example this is very unique idea and even in the current state it has been very useful at a customer. Almost completely vibe coded but idea is fully mine.
Making complete coherent products is as hard as ever, or even harder if you intend to trade robustness for max agentic velocity.
What I do very successfully is low stakes stuff for work (easy automations, small QoL improvements for our tooling, a drive-by small Jira plugin)
And then I do a lot of crazy exploring, or hyper-personal just for myself stuff that can only exist because I can now spawn and abandon it in a couple days instead of weeks or months.
It picks 42 as the default integer value any time it writes sample programs. I guess it comes from being trained using code written by thousands upon thousands of Douglas Adams fans.
Basically every ml script I see has 42 as the default seed, even before LLMs. Pretty sure it was what I used for my thesis code haha. So not surprising it always picks it.
Right on, I was going off the OP's GSD link, which looks like the def of a cli wrapper to me. Hadn't seen superpowers before, seems way too deterministic and convoluted, but you're right, not a cli wrapper.
There's a CLI tool that writes the agent skills into the right folder. The other option would be to have everybody manually unzip a download into a folder which they might not remember.
But there are still so many I can actually do that the opportunity cost of choosing any single one of them is infinite, and that leads to paralysis at worst and diluting your self while half-assing dozens of things at best.
Maybe one of them pays the bills, and even a nice house and a decent car. But it's just that, it is not what you really wanted to do, so you keep searching.
The "gift" of being a fast learner becomes a curse. In a few weeks you are an advanced beginner at almost anything. People marvel at how well you are doing, but you know you have just started and can now see how far you are from being any good. But to become good, you'd have to leave behind all the other things, and you can't pick. So you just start a new one for the quick dopamine hits and easy praise...
And then you are 50 and still don't know what you will do when you grow up.
reply