jetbalsa

My latest and greatest ThinkPad T14s Gen 6 likes to do it sometimes on cachyos, I can't nail it down from a KDE or hardware issue as it never does it while docked or a external mouse

I also noticed they where not using XML for game state output, from what I understand most LLMs still benefit from having outputs like this put into XML tags

with the keyboard typing and call center chatter... give me a break

I found it hard stops on /anything/ Ghidra related at all, its annoying...

I suspect their tar pits where not very good, most models can tell when you are feeding it junk, I see this a good bit with ollama honeypots,

I have not very well treated AuADHD and being alone with my thoughts very long is generally not very productive, At least Coding LLMs have helped me get things I wouldn't of had the attention span to make in the past come to life. and a good bit of vibe coding is just yelling at the LLM that what its doing sounds good on paper so keep going, please do the needful, make no mistakes :V

Depends, the SMD caps spread across the board the tiny ones do start to fail and go out of spec over time. they are a right pain to replace and hard to spot one that has gone out of spec to cause the chip to start crashing.

Thats why I've always like pytk

    from tkinter import \*

    root = Tk()
    a = Label(root, text ="Hello World")
    a.pack()

    root.mainloop()

Who are you again?

I've had a "Get in loser, we are going to Tau Ceti" on my car's bumper ever since the book came out

Ah, The 4chan of Minecraft servers, a silly place.

VPN and DNS Packages in OpenWRT eat a good bit of ram. and sometimes can be cheaper for faster speeds needed to higher packet processing.

I think they are looking for full 2d graphics, bitmaps, sprites and the likes.

always wanted to see if this was doable using NBD or even RBD over the internet. but I do love the ESP32 device they came up with.

I know a guy who gets a bunch of old hardware as a recycler, We made the Shell On Demand Appliance for DEFCON[1] awhile back and would love to expand it, but power/internet would just cost too much. we have the hardware and software to do this. just not the long term recurring

[1] https://forum.defcon.org/node/246908

I've been mostly using Kimi has a hacker of sorts, putting it places I want to attach AI directly as their API for their plans are not completely user hostile. Need to do OCR for scanning Magic the Gathering Cards. Sure!, have it attached to X4: Foundations as a AI manager for some stuff. sounds fun. Can't really do that with claude

That or having it start shit posting about your crappy code base on https://moltshit.com

Yep, Its pretty damn good compared to classic OCR and even more lightweight ones as well that I can run locally. the cards just vary too much over time.

I'm unsure of the sizes needed for prompt cache, but I suspect its several gigs in size (A percentage of the model weight size), how would the user upload this every time they started a resumed a old idle session, also are they going to save /every/ session you do this with?

The cache is stored on Antropics servers, since its a save state of the LLM's weights at the time of processing. its several gigs in size. Every SINGLE TIME you send a message and its a cache miss you have to reprocess the entire message again eating up tons of tokens in the process

So to defend a litte, its a Cache, it has to go somewhere, its a save state of the model's inner workings at the time of the last message. so if it expires, it has to process the whole thing again. most people don't understand that every message the ENTIRE history of the conversion is processed again and again without that cache. That conversion might of hit several gigs worth of model weights and are you expecting them to keep that around for /all/ of your conversions you have had with it in separate sessions?

The cache is on Antropics server, its like a freeze frame of the LLM inner workings at the time. the LLM can pick up directly from this save state. as you can guess this save state has bits of the underlying model, their secret sauce. so it cannot be saved locally...

Oh god yes, I've been trying to make a LLM Assisted Magic the Gathering card scanner... its been a hell of a time trying to get it to just OCR card names well....

i will note that they really should of used something like ncurses and kept the animations down, TTYs are NOT meant to do the level of crazy modern TUIs are trying to pull off, there is just too many terminal emulators out there that just don't like the weird control codes being sent around.

That is why Typescript is the main one used by most people vibe coding, The LLMs do like to work around the type engine in it sometimes, but strong typing and linting can help a ton in it.

I am kind of doing that now. I put Kimi K2.5 into a Ralph Loop to make a Screeps.com AI. So far its been awful at it. If you want to track its progress, I have its dashboard at https://balsa.info

What where you using it for? claude is really good at agentic stuff, Pure coding, I can see codex being better, but for the entire workflow, I'm not sure

there are ways to help with lag a bit, you can choose the number of hops a HS uses when meeting up. but of course that comes with downsides

I'm spitballing here, but I suspect that (same with AWS) google uses post processing for billing, they run a job that scrapes the states THEN bills you for that. instead of the major AI companies are checking billing every API request coming in.

I like using put together a program, that sounds just about right for our current AI Overlords