AgentMatrixAI

Reading this makes me sad at how different my generation was compared to the new ones.

I remember when Counterstrike 1.3 came out and everybody at my school were talking about it and playing it. We would line up at computer labs before lunch started, pay a toonie and entire room would crackle with in-game radio comms, AK47 and HE going off with a room full of people side by side excitedly shouting for an hour until lunch was over.

When classes finished we would head back to the lab again and we would play endless round of de_dust 1 & 2, de_rats, fy_iceworld and the occasional as_oilrig and the rush of being the VIP and experiencing my first headshot.

Sometimes the admin running the labs would add fun mods like no gravity and weird stuff....

It was such a memorable and social fun time and it runs in complete contrast to the everything-gambling culture that has taken foothold....

First time making something 3D and code wise, codex has been very useful, even creating a in-game 3D editor as well as netcode

The trickiest part is really using 3D and it comes with lot of extra scoping you normally take for granted: animation, uv texture, rigging for humanoids, making sure stuff doesn't clip through etc.

Still learning Blender but its very slow. I haven't tried the MCP for it yet but I want to get proficient at it to be able to produce psx graphic models and textures...

amazing timing! been needing something like this since Blender has been tough.

I've been working on a cybercafe simulator with Three.js and codex and animation is hard to get right

https://x.com/AgentifySH/status/1981761490274464068

Anybody else just wrapping SOPS in a rest api call and using that? Feel like that is just as good from my experience. While I think Vault is useful for large companies, I just need something to encrypt and decrypt and not rely on pgycrypto

I'm not really convinced, the benchmark blunder was really strange but the demos were quite underwhelming, and it appears this was reflected by a huge market correction in the betting markets as to who will have the best AI by end of the year.

What excites me now is that Gemini 3.0 or some answer from Google is coming soon and that will be the one I will actually end up using. It seems like the last mover in the LLM race is more advantageous.

While you could do that, proxmox offers lot of value with its UI which I need to default to time to time. With just an API key I generate from proxmox I have a wide range of capability that I can hook up an MCP server to.

The funny thing is with Cursor I can just generate a new capability, like the clone and template actions were created after asking Sonnet 4.

haven't tried Qwen but used these "near instant token" like groq and another one that uses diffusion model to generate code via LLaMA and the results weren't satisfactory.

now if something like Gemini 2.5 pro or Sonnet 4 even can run on Cerebras generating tens of thousands of code in a few seconds, that could really make a difference.

it gives me a direct bridge from cursor -> VM, for local dev & test out open source projects

I like having a local server I can carry with me and control using just Cursor to manage it.

So basically the freedom that comes with a homelab without using proxmox UI and ssh.

Been using proxmox for a home lab and I still can't believe how much value they provide for free.

I use it with Cursor and create vm templates and clone them with a proxmox MCP server I've been adding features to and it's been incredibly satisfying to just prompt "create template from vm 552 and clone a full VM with it".

https://github.com/agentify-sh/cursor-proxmox-mcp

So they are profiling people using Pixel phones with GrapheneOS....because its good at what it does? Am I reading this right?

I'm not so optimistic as someone that works on agents for businesses and creating tools for it. The leap from low 90s to 99% is classic last mile problem for LLM agents. The more generic and spread an agent is (can-do-it-all) the more likely it will fail and disappoint.

Can't help but feel many are optimizing happy paths in their demos and hiding the true reality. Doesn't mean there isn't a place for agents but rather how we view them and their potential impact needs to be separated from those that benefit from hype.

just my two cents

What % of cloudflare's protection can this provide? I've been looking at bunkerweb + anubis as alternative to cloudflare tunnel (im actually not sure if this provides WAF)

Prompt quality and knowing your domain is critical. One issue I had early on was experimenting with LLMs to generate a frontend application in a brand new framework I was unfamiliar with (Svelte at the time) which lead to situations where I would cruise along and get stuck in a loop. The other issue came from the increasing context size that led to more unpredictable behaviors (i would ask it to change the color of a button and it would completely change the entire page).

almost all the tools i've used to date for designing frontend framework, none really replaces using cursor and being able to dive deep, however cline does seem to have gotten significantly better.

the day where you can come back to a fully working web app with moderate complexity after cleaning the gutter is still some way off but thats the dream

forgot the name of the watch but it had an lcd display to save battery and a full touchscreen around 2017? i ended up using the lcd display mostly for HB and walk distance. it would be great if we had a completely e-ink based pebble watch with backlighting (lcd display was great but couldn't be viewed in the dark :/)