I’m selfhosting it on box next to me. Wasn’t so hard for me to find the GitHub link on their website.

They have a SaaS option as well, I’m guessing that’s the main revenue plan.

Huly is pretty amazing and has a self host option. It supports chats and video calls, team rooms, and has some cool integration for speech to text note taking. It also functions as a task tracker.

Under super active development right now so host only if you can deal with occasional breaking changes.

Hey that’s awesome! thank you for the share. Planning to install proxmox this weekend and give it a try.

Having electric stability issues this week in Bangkok - several 2-3 hour outages, which are too long for a UPS to cover the gap. I have several mid range but older PCs running docker, virtualbox, etc for various things including a postfix server for the family email, immich, QBittorrent, pihole, paperless, huly, postiz, a Minecraft bedrock server, a flightradar24 ads-b collector, and a variety of other homegrown projects.

Thinking about getting some or most of this over to a service like hetzner, perhaps even splurging on a baremetal dedicated system.

Recently I’ve been reading about/trying to learn qemu and proxmox, but don’t understand them yet. Is that where it’s at for managing a bunch of your own VMs? Or kubernetes/k8s?

I’ve been a little out of the loop for a few years and of course coming back up to speed IT wise judge take weeks. Looking for recommendations on offloading my home stuff to a cloud that I control.

I’ve heard of vibe coding but in the context of being able to identify music that fits a “vibe”. What are you talking about?

This is when you give some LLM a prompt such as “write a game like Minecraft except cooler” and the system will output some code that might run and might vaguely resemble a block game.

So then you go back ask for more, it does something to the code potentially improving or breaking it, go back again ask for more, and repeat over and over. I’m being a little bit sarcastic because most serious developers look down on this, but really this is how a lot of coding is happening these days. There are tools to make this process somewhat usable and they are getting better every day.

Interesting. I can buy that idea, a model that’s designed to be general and answer all questions is going to have to make compromises in a lot of ways.

So it’s possible that model benchmarking needs to be revised in some way to give more useful analysis of its capabilities.

The industry is quickly moving towards using agents, MCP connections (sources of real-time data for the model to pull from, and apis that allow the model to perform tasks, like putting things on a calendar), and RAGs (augmentation with sources of truth, such as a 100 page pdf guide for example), and models that seem to be more aware that they can get data from other sources.

The future might become specialized models all the way down.

Just today I’m playing with “vibe coding” and using one agent as an orchestrator that assigns and monitors tasks to other agents. The result is still slightly bullshit code but it’s amusing to watch it work. Not sure yet if this is a strategy to spend all my money through API fees or will result in something useful 😂

You can do due diligence as a buyer forever but if the seller lies or doesn’t disclose… Problems like these happen. Lawsuits are potentially incoming to figure that one out.

It kind of looks like the new owners of VPN Secure got screwed - the last owner made all these costly lifetime deals and didn’t tell them. The obligation/liability to service those deals wasn’t transferred to the new owners.

Which means the old owner is probably the bad guy here and still owes these customers for their lifetime subscriptions.

Just curious if you’re a developer or using LLMs often.

I like Anthropic’s sonnet 3.7 model for agent and code related tasks more than the Open AI models at the moment.

Deepseek and LLama can be run offline, which is great for certain uses especially the aforementioned BS tasks that can perhaps burn through API tokens. Quality of output doesn’t match the top models but this is second to privacy for many.

Not sure where things are at with Dall-E 3 image generation but the last time I was looking it seemed like Stable Diffusion has gotten damn good and is extensible in ways that dall-e is not.

Voice recognition, and TTS output w/emotion OpenAI has the best I’ve ever heard.

Image recognition openAI might lead but the llama4 multimodal stuff is pretty awesome

Anyways I’m just some rando but my observation is that OpenAI better get on that IPO fast unless they have some magic in the pipeline because they are being attacked by competent solutions from every side in a niche that is showing diminshing promise to change everything the father we go.

A lot of their staff will be finished with needing to make any money ever again in their lives if they IPO.

But that will also throw OpenAI into the public sphere of needing to make money quarter after quarter forever, which inevitably leads to them sucking and no longer being innovative. Actually OpenAI is already teetering on this already as others are catching up. Sam and other top guys will leave because they hate people telling them what to do and don’t need it.

Facebook and Deepseek are literally giving it away for free now to kill the competition and in some areas other competitors are producing better products already.

It’s a weird space. I used to think we were on the verge of entering a whole new era of technology but now I think it’s going to be muted. Perhaps AI (as we know it now) eased some tasks and eliminated some BS stuff that used to waste our time, but we’ve not yet completely eliminated most professional jobs - if anything I think we just added more for them to learn and do to remain competitive.

GTA 6 is just going to be client app to a universe of micro transactions. They should probably just give it away free.

Here’s another take. I think some people would never act cruel towards their equal yet they can easily act cruel if they believe another human to be someone less than their equal.

This is why during war times it is common to develop nasty names and personas of the individual enemies.