Still some way to go until we run "it" on our own machines. Even with current "mid to high end" hardware you barely reach the same quality and speed with a free LLM compared to what Opus or Astra delivers. In numbers: A 3k Euro Macbook with 32 GB RAM allows you to run a (hard guess only) up to 16 GB Model. Alone! Not speaking about sub agents here. Because you still need memory for your everday work and other programs, cache, context etc.
Well, if there is demand, it will be possible over time. 3D graphics also went from each frame being generated for hours on a compute farm to real time 3D games running on a phone.
From my experience, there is no everlasting digital system, no matter how many fallbacks you add. So I wonder, how can you ensure, this still works after e. g. 1 year?
The system checks with contacts after one year to reconfirm. If I don't receive my weekly check-in email I check the server. This is a best effort attempt to ensure business continuity for me if I'm dead. It's better than not having a plan for me. There's a health address you can point to that checks the system is working from an outside monitor. :)
Yea.."art performance" kind of already catches it. I want to see what people can do with just HTML, JavaScript and CSS. Like back in the days, withouth subscriptions, algorithms, bloat.
It certainly sounds interesting, but then I wonder: After a couple of days or maybe weeks, even with a sophisticated knowledge management strategy, the knowledge of Wilmund is so big, that there won' t be much room left in the context window. Right?
i've got my coding agents looping over 64k-128k of context continually by dynamic context pruning that either compresses context via summary or evicts context via waypoints.
It seems to be able to do rather long context runs and feature implementation. It's cleary not perfect, it forgets some things, but it's able to process a direction and stay on that direction for long spans of time.
Technically, you can have a simple directive and not need all the context in the world to act. Same way people forget things when they enter through doors, people arn't always acting on all the context in the world.
But this stuff is still dumb from the tools I see most people using.
Hot take: Right now it's quite simple to loose customers, like customer churn from A to B or back. That's the weakest spot, isn't it? No matter how complex the products grown and how deep they are integrated into our systems, common users can easily switch. Even heavy users, I argue. Just tell Codex to rewrite the existing Claude-instructions into their own. Even that may not be necessary, if you organized your work "agent agnostic".
And I dont see how that could change, that's why they try to offer tools that are even more integrated into our lives. Like "dots". But this also narrows down the use cases and client base, I argue.
When working with a whole bunch of sub-agents, like you probably would do when coding, 2-3 sessions at a time are probably not enough. Like I build very specific sub-agents for code review, ui review and so on. Within one project I work with at least 3 - 4 agents then. Using Opus on every task would not leave room for other everyday-tasks.
good to have a quick overview, though I am missing some kind of depth, like
>There are others — MLX-native runtimes, llama.cpp directly — but Ollama and LM Studio cover 95% of people reading this.
Sure, but... MLX native runtime have a lot of advantages right? and they are not necessarily more complicated like eg ollama. It's worth to mention them, too.
Coming to the next missing part: use cases.
Running it locally competes with dozens of freely available chat bots. And for most simple parts, seriously, you don't need that sophisticated payed AI service. But then: how do local model's perform exactly here: let's start with coding, image generation and more? Like stuff that I probably really want to run locally.
I don't know.... With all those approaches to run AI in your own premise, people need their own hardware. It makes them independent. Of course hyperscalers and AI labs don't like that, but I argue that consumers prefer independence over some costs of operations. If this would be the case, people wouldn't own cars.
I am quite familiar with Resolve..I am not a pro, and it's probably totally overload for my purpose, but I think it's easy to learn and even quite intuitive
I tried many others, but mostly all others are not stable enough or have an even worse UI/UX... so I wonder... is this different?
I’m also not pro and just need an editor for Youtube or work. I think open source editors like Openshot and Kdenlive are generally underrated and easier to use than they used to be but even for just cutting together clips, adding text, and using keyframes it’s hard to beat how nice Resolve is.
reply