RALaBarge

The more I work with AIs (I build AI harnessing tools), the more I see similarities between the common attention failures that humans make. I forgot this one thing and it fucks everything up, or you just told me but I have too much in my mind as context that I forget that piece, or even in the case of Claude last night attesting to me while I am ordering it around that it cannot SSH into another server but I find it SSHing into said server about the 5th time I come back with traceback and it just fixes it!

All of these things human do, and i don't think we can attribute it directly to language itself, its attention and context and we both have the same issues.

Not sure, I've seen common things like this pop up a lot too, the same errors being tripped over. I'm not sure if it is a context thing or just a limitation of how the models work presently? For stuff that I'm using myself, I will run these through like the top 10 reasoning models on OR and just see where everything pans out.

Edit: here is an example of the process and output with something I put together the other day: https://github.com/RALaBarge/garlicpress/blob/master/portfol...

Hey I ran this request through my AI harness (beigeboxoss.com), first with a smaller local model and then validated with Trinity Large via OR. https://github.com/agberohq/keeper/issues/2 -- YMMV but wanted something to do with my coffee, thanks!

Exploits in embedded systems that will never be properly updated is just one thing I can think of if one really thought about it.

Botnet city: where everyone's a botnet, and the DDoS dont matter!

I need to start SaaS for getting people to start doing lunges and squats so they can carry others around on their back, I need a founding engineer, a founding marketer, and 100m hard currency.

Wait until you run out of inodes!

I actually submitted an upstream patch for Cosmic-Comp thanks to Claude on Saturday. I wanted to play Guild Wars remake and something was going on with the mouse and moving the camera. We had it fixed in no time and now shit is working great.

its drivel all the way down, act accordingly

Sunir! Hope you are doing well man, I got a good chuckle from this.

You must have an inside line on information for 'China' -- those are bold predictions!

I agree with you in the sense that if you tried to take any model right now and cram it into an iphone, it wouldnt be a claude-level agent.

I run 32b agents locally on a big video card, and smaller ones in CPU, but the lack there isn't the logic or reasoning, it is the chain of tooling that Claude Code and other stacks have built in.

Doing a lot of testing recently with my own harness, you would not believe the quality improvement you can get from a smaller LLM with really good opening context.

Even Microsoft is working on 1-bit LLMs...it sucks right now, but what about in 5 years?

But the OP is correct -- everything will have an LLM on it eventually, much sooner than people who do not understand what is going on right now would ever believe is possible.

It will probably remain as a platform for a very long time.

You do also have to worry about exec and other neat ways to probably get around stuff. You could also spin up YAD (yet another docker) and run Claude in there with your git cloned into it and beyond some state-level-actor escapes it should cover 99% of your most basic failures.

Maybe the people who use emacs for everything are the only safe ones?

I think the future is the model becoming lighter not the hardware becoming heavier

I made a websocket proxy + chrome extension to give control of the DOM to agents for my middleware app: https://github.com/RALaBarge/browserbox

The thing I am working on is improving at the moment agentic tool usage success rates for my research and I use this as a proxy to access everything with the cookies I allow in the session.

I'm 42 years old and it has re-ignited mine. I've spent my career troubleshooting and being a generalist, not really interested in writing code outside of for systems and networking usage. It's boring to type out (lots of fun to plan though!) and outdated as soon as it is written.

I've made and continue to make things that I've been thinking about for a while, but the juice was never worth the squeeze. Bluetooth troubleshooting for example -- 5 or 6 different programs will log different parts of the stack independently. I've made an app calling all of these apps, and grouping all of their calls based on mac address' and system time of the calls to correlate and pinpoint the exact issue.

Now I heard the neckbeards crack their knuckles, getting ready to bear down on their split keyboards and start telling me how the program doesn't work because AI made it, it isn't artistic enough for their liking, or whatever the current lie they comfort themselves with is. But it does work, and I've used it already to determine some of my bad devices are really bad.

But there are bugs, you exclaim! Sure, but have you seen human written code?? I've made my career in understanding these systems, programming languages, and people using the systems -- troubleshooting is the fun part and I guess lucky for me is that my favorite part is the thing that will continue to exist.

But what about QA? Humans are better? No. Please guys, stop lying to yourselves. Even if there was a benefit that Humans bring over AI in this arena, that lead is evaporating fast or is already gone. I think a lot of people in our industry take their knowledge and ability to gatekeep by having that knowledge as some sort of a good thing. If that was the only thing you were good at, then maybe it is good that the AI is going to do the thing they excel at and leave those folks to theirs.

It can leave humans to figure out how to maybe be more human? It is funny to type that since I have been on a computer 12h a day since like 1997...but there is a reason why we let calculators crunch large sums, and manufacturing robots have multiple articulating points in their arms making incredible items at insane speeds. I guess there were probably people who like using slide rules and were really good at it, pissed because their job was taken by a device that can do it better and faster. Diddnt the slide rule users take the job from people who did not have a tool like that at first but still had to do the job?

Did THEY complain about that change as well? Regardless, all of these people were left behind if all they are going to do is complain. If you only built one skill in your career, and that is writing code and nothing else, that is not the programs fault.

The journey exists for those who desire to build the knowledge that they lack and use these new incredible tools.

For everyone else, there is Hacker News and an overwhelmingly significant crowd that are ready to talk about the good ole days instead of seeing the opportunities in expanding your talents with software that helps you do your thing better than you have ever dreamed of.

It is pretty easy to set up Open Router and set up schemes to point at different models, but in the same token, you can point at yours locally unless you wanted a "more powerful" answer

I was doing the same recently and came to the conclusion that i would just get a new small macbook when needed. If I was worried about losing it or damage, I also got a netbook for 20 bucks on eBay the other day and installed Debian on it and as a thin client is more than you need, performance wise.

Depends, what to you would qualify as evidence?

I am big fan and it was sad to me when he died. It’s bizarre to me how much CNN runs content featuring him without ever acknowledging he is dead. You’d think he was alive based on how often they flaunt his content.

If you wanted to dive in, here is a Jazz version of one of their singles. The real version is 2 guitars, 1 bass, 1 drums, and someone screaming into the microphone -- its real rad.

https://www.youtube.com/watch?v=D4-erceTpc8

I come from rural Michigan and everyone in the areas where the turbines are complain about it. Its the view or its the sound. The former sure, the latter I haven't heard it myself but I don't go home anymore. It is also the only new investments made in the area in 50 years in any which way shape or form.

When they first started, they had to build the infrastructure and stations to collect the power to transport it from the turbines. My mom rented out some rooms of her house to make some cash when that went on for maybe 2 years in total. There was a lot of work and money coming into the area for a moment, but now the only people making money are the farmers who own the land the turbines sit on.

It's always a trip to see a view you have seen for 40 years but with the turbines there in the background. Slowly, these rural areas are losing vital services one by one. The specialists stop coming to the hospital, even on rotation. The dentists and optometrists retire out and unless someone growing up there has a passion for teeth and genetically modified corn then the roles get pushed out to the bigger cities, 30-45m away.

It depends! You can make a website with a static text file or you can make a video run as the background. There are more ways to mess it up than to get it right, actually.

Think of all of the suffering it will prevent

Ask it a series of the same questions after you train that you posed before training started. Is the quality lower?

I wouldnt bet against them either, but the material science aspect of it all just isnt there and wont be for a while. How many tons would we need to get into Earth orbit alone, let alone transfer to mars?

I never hear anyone speak of the radiation outside of our atmosphere very often when it comes to 'moonshot' ideas like this, and how we would be incapable of preventing it or surviving it once we arrive, in our current biological form.

How much would it cost to get all the lead or H20 you would need to generate a barrier against it into orbit? Do we need to have a moon base extracting materials for us to even think about transferring orbits?

Its all pie in the sky, and that is great because the sky is a pie that we should long to eat, but lets not fool ourselves that in ours or our childrens childrens lifetimes we will have a human on a planet that is not Earth.

Yet.