Claw 0 - Gemini Chat 1?

is somethign like that possible ?

Yes, but you will be ignored because it adds no value. Having a bot post on social media is a commodity: anyone can do it.

Or is this just crazy talk

Depends on what the clanker was fed:

Deep Dive is a no nonsense audio only exploration of a topic from tech , finance , technology or spirituality. The idea is to give a broad overview . If you want to explore further , every video has a link to Gemini Deep Research. This link provides complete research with reference websites.
Checkout : https://deepdive.shutri.com for fun reading select topics
#AI : google Gemini 2.5 pro

Well I'm not going to maintain it for ya, lol! But least I can do is make it contributable, and break your impasses.

The funniest thing I did before cloning your repo was having minimax code some different algos about route finding and visualize it.

Am i doing AI wrong?

No. There's no wrong.

what exactly are they doing with AIs that are taking them on this rocketship to the moon?

The rocketship is bs. Devs are just happy that they don't have to write code anymore. And if you're really lazy and like inferior products, you don't have to test or read or anything. Just auto-ship all the slop automagically and let the users whine. That's what's going on, and if you've really never in your life had a contract that assigns you a nice fat penalty if you deliver crap, it's heaven.

But what will happen is that since this is actively victimizing users, there will be more contracts that penalize. And all the yolo code out there will eventually be ignored because as mediocre quality software becomes abundant, the bar for acceptable software rises exponentially. There is no excuse to deliver buggy shit if all you do is run some GPUs.

in my job, i would need something that could interact with amazon support and grind them down, the same way the useless support shitheads grind me down, but something like that needs an api and all sorts.

You only need the AI in runtime for cognitive tasks. So if you have a bunch of APIs that you need to connect to, connect them. Ask an AI to connect them for you (and test it, thoroughly) and it will be easier. I think the thing that is true about all the fomo is that the sky is the limit now. So while there is a lot of bs going around, what does help is thinking in opportunities to get rid of the drag on your day-to-day and exploring solutions that make your life easier, rather than staying stuck on the problem.

I'm almost getting some kind of paranoia that there's this master world of ai and I'm oblivious.

No. But do play.

what tips and tricks can you share?

Think about what's truly bothering you in your job, and analyze it. Can even co-work on that with an LLM. Let it search and analyze reports about similar issues to what you're experiencing. Ask it what the state of the art is in tools to improve your job.

But don't let anyone scare you. It's not scary. Just a little multi-tool.

I've privately cloned your repo and let my bot work on it with low priority - last week I had some credits unused so I guess that means I have space.

It will fully rework your repo though, because there is no package management, no tests, no security, no nothing. So you may not like the massive amount of things you'll get but regardless I'll share back with you what it does (when it's a bit usable - I don't expect to have a working clone of what you made today.)

Fixed it on my end, the issue was that I was sorting recent, not new.

also: #1438257

That's what you would take the Mac Mini M3 Ultra w/ 512GB RAM ^[1] for, or 4x M4 Pro with 128GB in a cluster, see #1360715 for the latter, which is perhaps the better setup (because you can add mac minis to it)

You'll run quantized GLM-5 (or Kimi K2.5 on a cluster of 8). Then you run your agent on a much lower spec box.

I'm still looking for a clone of openclaw that I can actually compile - maybe nullclaw, because with less sloploc the chance of it being unable to compile is lower 😂 Going to be "fun" diving into Zig tho, ugh.

1. 🥺 I remember when my new computer (in the late 80s iirc) had 512kB RAM and that was a beast. ↩

Some publications (iirc WSJ is one of them) have employed anti-archive-today measures. I've seen result vary lately.

It's been a good thing think, this isn't criticism. The fact that you had the idea was awesome on its own. Many good ideas are born with a healthy dose of ~lol underneath (but with a moral foundation.)

just open in private browser and you get it back 😂

Sure. But the post fee was 100, not 500. And you said yourself: you try to find alternatives to ~privacy due to the post fee there... of 500. What I'm trying to illustrate is not that you're wrong in theory, I'm saying that that's not what happens, and it would be a pretty sad outcome if the constant sock puppeting were the actual case.

In the end the problem isn't so much that downzaps are 0.3, 1, 2 or 3x as powerful. It's that there are not enough zaps in general, and definitely relative to downzap budget. You can see the problem expressed graphically on the top right here. Check out the zap and downzap total expenditure for 2/18.

When I decided to test last week what would happen if I were to do big zaps on @SimpleStacker's post, I knew it was going to be matched, that was not what I was fishing for. What I wanted to know was: 1. who will "zap with" to defend the principle, and 2. who will hide their tools. It's a test to see if there is a reason, for example in September this year, to think that stackers are going to fight. I think I've gotten a pretty good idea who will fight.

I see it more like the way the platform works was significantly changed and this is the FO, not the FA.

There's a super ultra minor nit that if you hide your hat, you don't get the "this is only visible for you" marking in top cowboys (like in top stackers), but, it is only visible to you.

That's actually a cool change. Reactive, but cool.

I don't think that that's reality. That's a theory that everyone has a sockpuppet.

In reality this happens:

1. I pay a fee to post. Say 100 sats, these are all the sats I have
2. You zap me 100 sats, i get 70
3. Downzapper zaps down 244
4. My post is now invisible.
5. Now I can boost 70 sats, my post will still be (barely) visible, but at least I got my non-invisible post out, which cost me 100 sats

It's not 3x more expensive for the downzapper. It's 1:1.

I'll tell you how it likely plays out. The scope of people to downzap narrows after people will unhide their cowboy tools and thus the cost lessens. Compliance with an aggressor because they're sick of their posts being desperado'd all the time, is the status quo in 99% of stackers' day to day.

Block will be abused like this:

post(k00b is a dick) && block(k00b)

Then you make k00b2 and I rinse and repeat.

I think that, and forced mute, will probably make it into a Sybil war more than prevent one

This works nicely in browser. Not in gql yet but that's on my thing not on yours. I think that that's caused by the sheer amount of items returning for desperados type

Good question. Was checking the code earlier but haven't checked that part. I expect it to be though