HackerLangs
TopNewTrendsCommentsPastAskShowJobs

AndyNemmity

2,118 karmajoined 15 lat temu

Submissions

Made an 82-0 style game for wrestling

5starbooker.com
2 points·by AndyNemmity·29 dni temu·1 comments

Why Does Your AI Agent Work Better for You Than for Me?

vexjoy.com
1 points·by AndyNemmity·2 miesiące temu·0 comments

The Crypto Coin was the tell – thoughts on GSD, and it's crypto rugpull

vexjoy.com
2 points·by AndyNemmity·2 miesiące temu·0 comments

55 Hours of Codex /Goal: What a Port Task Teaches You About Autonomous Loops

vexjoy.com
2 points·by AndyNemmity·2 miesiące temu·0 comments

Richard Dawkins (AI) Refutes Richard Dawkins (Human) on AI Conciousness

vexjoy.com
3 points·by AndyNemmity·2 miesiące temu·0 comments

Cloud Skills Are Still Just Skills

vexjoy.com
1 points·by AndyNemmity·2 miesiące temu·1 comments

Adaptive Thinking Doesn't Change Quality. It Changes Variance

vexjoy.com
1 points·by AndyNemmity·3 miesiące temu·0 comments

Tell the Model What to Do, Not What to Avoid

vexjoy.com
1 points·by AndyNemmity·3 miesiące temu·0 comments

8 months ago when agents came out, I build an anarchist AI agent collective

github.com
2 points·by AndyNemmity·4 miesiące temu·1 comments

I Was Excited to See Someone Else Build a /Do Router, but Then

vexjoy.com
1 points·by AndyNemmity·4 miesiące temu·0 comments

Show HN: Yet another Claude Code agent setup, but several noval patterns

github.com
1 points·by AndyNemmity·4 miesiące temu·1 comments

My Claude Code setup you definitely shouldn't use. It's AI Overkill

github.com
8 points·by AndyNemmity·4 miesiące temu·0 comments

The Handyman Principle: Why Your AI Forgets Everything

vexjoy.com
3 points·by AndyNemmity·6 miesięcy temu·1 comments

Everything That Can Be Deterministic, Should Be: My Claude Code Setup

vexjoy.com
2 points·by AndyNemmity·6 miesięcy temu·0 comments

Everything That Can Be Deterministic, Should Be

vexjoy.com
1 points·by AndyNemmity·6 miesięcy temu·3 comments

The /Do Router: Keyword Matching for Specialist Selection in Claude Code

vexjoy.com
2 points·by AndyNemmity·7 miesięcy temu·1 comments

Show HN: A week of progress making a game in Claude Code without any coding

play.wrestlejoy.com
1 points·by AndyNemmity·7 miesięcy temu·1 comments

comments

AndyNemmity
·przedwczoraj·discuss
I don't want to turn this into an, oh look at mine.

It's just always been very behind the curve. I don't think you should use anyone's honestly. You should create your own shell base, and point to skills you find might add value, and add them. Then as you learn things about the shape of how things work, what you end up doing is rewriting them to follow your rules from what you learned.

What you'll find is, you'll have significantly better skills and systems.
AndyNemmity
·3 dni temu·discuss
That's funny, cause I'd argue superpowers barely does anything, and you need a much more complex setup to gain value.
AndyNemmity
·7 dni temu·discuss
I like my setup, and don't feel productive without it, but I find it very complex to new users, and mostly only software engineers use it.

https://github.com/notque/vexjoy-agent
AndyNemmity
·13 dni temu·discuss
Very interesting story. I come from a different direction.

I work in tech, and was onsite somewhere for over a month with nothing to do. Remote area. I had always loved magic, and had asked magic teachers to teach me when I was a kid, and they all said no, they don't teach anyone.

I read books, but didn't really get it.

So I was in tech, in a place completely foreign to me with no rental car on weekends. I asked the bartender if he had anything I could do. He handed me a deck of cards.

From there, I just started to learn and practice things cause I was bored. Ultimately went to train with Jeff McBride and Eugene Burger. Jeff wasn't focused on the kinds of magic I liked, and Eugene Burger hated my style. I fooled both of them for the "final", intentionally leading Eugene down a garden path.

He hated not treated the cards with reverence. So I threw cards behind me, knowing it would completely shut off his brain while I did the secret move.

I did the same with Jeff. In the routine, I took his teaching on what not to do, and intentionally did it to shut off his brain.

They were both completely, ridiculously fooled. I likely may have fooled them without it, but I am too clever for my own good, and wanted to trick them in my own way.

From there, I ended up training with the guy who actually fit my style, Dani Daortiz. I flew to Spain and learned from him and Yann Frisch. I also helped Yann develop a new move. I taught them some of my original moves which they loved. I just come at things from a very different angle, so I have some interesting things.

Dani asked me to perform at the end, but I was too nervous. He is the guy I most adore. I regret that.

I even left them at one point after a full day of working with them, and just went and did magic in Spain for the night. I just do whatever, and that was what my soul needed after listening to 12 hours of magic discussion.

So I'm a software engineer, who has it as a hobby, but whenever I do it, I do it at a level that is stupid good. I don't even remember tricks, or have a set list, I just sort of vibe with whatever I remember, and rely on all the random skills I have to get there. I will do Lennart's snap deal for fun, invent a new trick on the spot because I'm bored. I do have a few original tricks that are completely mine.

One of them has a mind reading plot with cards. I have done the trick so many times in life, that I can legitimately forget the card, and it's fine, I can actually do the activity of figuring out their card without knowing it a good percentage of time.

You just get so used to understanding how people react to things, that you can figure it out in the process.

The trick just keeps evolving. Now, quite often, I have other spectators figure out the card. They also can get it with my... direction to what to look for.

So then they get to be the star. Lot of fun. It has so many variations because the whole thing is jazzed. So every time something new works, it's another thing I might remember to do.

I also am maybe the only magician then will intentionally bomb tricks. I learned early on that I do this for fun, and unfun people are not worth my time.

So even though I know the trick, and their card, I will intentionally pretend I don't and bomb the trick. I like that space. Living in that space has taught me more than any book about how to jazz around failure.

Intentionally failing is a master class in the space of failure in magic.

So I'm just a software engineer, who has had a ridiculously deep hobby for a long enough time that I can do a full show at a moment's notice. I have the tools, the understanding, and I can do prepared stuff, jazz whatever, or remember a trick i haven't done in 10 years, and decide to do that.

I do it for my fun. It's enabled me to drink for free where ever I go if I want, and have an enjoyable time.

I don't usually do the Magic Live stuff. I did that stuff for awhile, but I never felt like it really added much value to my experience.

I feel like I could surely if I cared to, book a show here locally, and do it. It would teach me a lot, but I just don't really want it. I like just being a random dude who can do ridiculously good magic when I feel like it.
AndyNemmity
·22 dni temu·discuss
Yeah, I also cannot get a perfect faro consistently enough. I can consistently get 51 cards correct every time. It’s actually amazing how I am off by one every single one.

That’s a thing where when you know how hard the trick is, it makes it better.

Very cool your training.

And same on poker plots. I can do them infinite other cooler ways, so what’s the point?

The burnable 2nd I have. But it’s not the traditional 2nd. I have practiced and still practice the Richard Turner style 2nd, but I never do it in a performance. I use another path to get to the same result.

Wasn’t planning on Magic Live, but I should see where it is and when.
AndyNemmity
·22 dni temu·discuss
I never did it for money. I did it for free. My joy was in their joy.

My job was to heighten their experience, and to essentially act as a mini therapist enabling them to feel confident in their own decisions.

But I feel you. I did things entirely differently to everyone else. Which is why I thought it was an interesting story.
AndyNemmity
·22 dni temu·discuss
The interesting thing is, the cheating in mtg has always been so, ridiculously bad.

If anyone actually cared, and really learned the moves, it would be imperceptible, even on camera, but instead regularly players get caught doing the dumbest of obvious things, even while on camera.
AndyNemmity
·22 dni temu·discuss
One of the things is, I do magic, and used to do tarot.

I found the tarot readings were infinitely better to the person getting the reading when I just forced the results. So I did.

I still did all the things you're indicating about talking about specific personality, etc, as the patter to the concept.
AndyNemmity
·22 dni temu·discuss
not a lot of magic tricks. quite few actually. and it's interesting that it ruins the trick for you, because it's still a quite hard maneuver.

as a magician, I'm always still impressed when I see perfect faros.
AndyNemmity
·22 dni temu·discuss
This is why I Blind A/B test everything.

I burn a ton of tokens, but things actually have to prove their value. And the vast majority of things do not come close to doing so.

I have my own AI agent full of stuff. I blind A/B test everything, but I also don't think the results are all that useful as a signal to others.

Just because I Blind A/B test it 4 months ago, it's maybe not meaningful today.

Maybe the word choices I use dramatically impact things.

I do it, because I can prove the value, and see it with my own eyes. I don't even bother publishing the specific Blind A/B tests.

Also, I've seen other people try to Blind A/B test and get it very wrong. If your measurements aren't good, the test is meaningless.

I don't know. We're all working on these problems together. There's a lot of black magic (which is why I rely on hooks a lot). I'm sure I have tons of black magic, I have a large little AI Agent.

But what I know for certain, is it works for me. All it takes is for me to not use it, and I honestly don't know how everyone currently works with AI.

I will link it, but it is not an endorsement for what you do. Mostly only other software engineers use it. And it's so very specific to the things I have to do.

At best, maybe it sparks an idea for you to implement on your own.

https://github.com/notque/vexjoy-agent
AndyNemmity
·26 dni temu·discuss
Last week I've been working on 5 star booker, an 82-0 style wrestling booking game.

just hit 100k ppvs from people generating them

https://5starbooker.com/
AndyNemmity
·29 dni temu·discuss
Thought I would share, started on it 6 days ago.

About 8,500 people booked 38,000 shows and minted 26,000+ share cards on 5 Star Booker.

Having a lot of fun creating it.
AndyNemmity
·w zeszłym miesiącu·discuss
Kayfabe is the best way to describe it.
AndyNemmity
·w zeszłym miesiącu·discuss
I have had dynamic workflows in my agent for the past 9 months.

I am diffing Claude Code with them, I tend to agree with the analysis.

So far, versus my system, there are tradeoffs, but the dynamic workflows are over tuned to use way more agents that I have ever found add value.

It used 8 to diff our systems. I would have used 4, for example.
AndyNemmity
·2 miesiące temu·discuss
I really do run a/b tests. I really do test, and validate.

I do not believe me giving you that information is honest. If I do, I am pretending that you will get the same experience.

Maybe you're using a different model. Maybe you have stuff in your CLAUDE.md that will break it.

It is not honest to me to give you confidence in it, when no one can be confident in it.
AndyNemmity
·2 miesiące temu·discuss
Yeah, I think we're in a phase honestly where you shouldn't use anyone elses skills, and you should instead point your stuff at a repo with skills, have it really read it, and then ask what of value there is to potentially rewrite in your style based on your preferences.

I have a complex setup with a lot of things based around what I do. I don't know how anyone could reasonably get their head around any of it. It's a research project in itself.

So I tell people, please don't use it. Just point your claude code at it, and see if there's anything useful for you.
AndyNemmity
·2 miesiące temu·discuss
I run a lot of a/b testing. But I'm not sure showing it actually communicates all that much. Since these are non deterministic systems, even showing you an a/b test from when i made the decision a month ago, doesn't really mean a whole lot.

I agree we need more clear indications of value, I don't quite understand how to legitimately do that in a fair, and honest way.
AndyNemmity
·2 miesiące temu·discuss
Define obviously validation? What is the signal that tells you one is reasonable vs another?

I find the only way to do that is to look at it, if it passes some visual tests, try it, and then a/b test if it's any better than without it.
AndyNemmity
·2 miesiące temu·discuss
I watched all the Alphago games live, I've watched analysis of so many Alphago games.

I think one of the particulars about Go is how hard the player base took it. Far harder than chess did. Far harder than Starcraft did (although arguably, Alphastar wasn't even that good strategy wise, it was just better mechanically even with preventions. No one has adopted almost any of Alphastar's strategy)

Lee Sedol in particular was crushed by the experience.

Others found optimism and opportunity in it.

I don't think extrapolating the Go experience is all that useful across the board, although it does have some value, and perspective, and it was a fantastic article I enjoyed reading.

Games have cheating, because cheating is easier than getting better.

Before AI, there was rampant cheating. In Magic the gathering, it's shuffle cheating, or holding out cards, or whatever.

The ease at which you can cheat makes more cheaters. If you can get away with it, or if it's like Go, or Chess AI, it's trivial to do, and easy to not get caught.

Same with map hacking in Starcraft.

I don't know. I don't have any fully formed thoughts here, except that I think extrapolating the experience in this way is vastly overstating it's generalized impacts.

But I also could be very wrong. We are talking about predictions. No one can predict anything.

Predictions say more about you, and your perspective, than they do about reality.

But great read, enjoyed thinking about it all.
AndyNemmity
·2 miesiące temu·discuss
For sure, this is the pattern I use.

And I wish I could make even more deterministic. Maybe I can, but it can also be a bit challenging to sort.