cyanydeez

Just the inevitable power trip CEO culture. The only singularity appears to be the separation between rich and poor.

As far as I can tell, the only reason Apple's walled garden protects your privacy is because it's way more valuable that way.

...your information though, not the product. They'll sell you out if they get the right MBA.

...convienent.

i think the proper understanding of LLM based AI is "contexting"; we describe the world we want them to fill, we build/direct the outside context for them to understand, then "they" take off from there.

If we do a bad job building context, they do a horrible job contexting. People who have trouble working with AI have the same problem people have in general: if they can't figure out the context of the direction, then they make random decisions of doing anything. On the flip side, if you can build the proper context around a sufficiently powerful LLM, they can derive the context via the contexting they're good at.

This is why building documents, tests, and code all in some intent pattern via prompting allows them to do a significant amount of work a normal person would have a great effort t

well, let me know when they have proper context management, etc.

oh. they do. I built that. It's pretty fancy.

But there's still human direction behind most projects in the cybersphere.

https://github.com/peonist-ai/halogen-server is beating the pants off of anything I've tried.

38GB of vram resident. more tk/s, more prefill.

I'm pretty sure the point of Qwen3.8-Flash-Next was to get the open source engines to integrate the qwen4 architecture.

The fact that it basically broke open the local model supremacy was just a nice side effect.

I'm running: https://github.com/peonist-ai/halogen-server with a quant4, PLE offloaded, and it's resident VRAM is 36GB at 265k context.

Shave 10 more GB off and the TAM openai and anthropic are targeting is a lost cause. Local models are what 90% of people will need.

If the world governments can get a handle on the memory cartel, then there's no more moat for most normal humans.

I think WallE is the perfect reference for the world AI/oligarchy are running towards. Not whether it exists, but that' dependency+environmental destitution.

litterally, that's what an LLM is doing?

I also think we're seeing the sigmoid approaching.

I think it's a mistaken belief that AI as we found it is the exponential runaway train.

So it makes sense, since all you need is compute, that there's a ceiling and specialization is going to be more valuable then some super AGI.

Especially since the worst people seem to be the ones who think they'll all run away with the bag.

being in control is something people desire, but they dont seem to understand the actual costs.

I'm guessing it just has more to do with commiting and pushing and automatic CI builds.

Nothing about complexity, simply github setup such an easy automated system but AI cares not about whether their commit+push is going to kcik off a whole rebuild.

Same thing happens when I run docker build loops. The AI gives very little shit, unless I tell it, about not busting cache; so it'll sit there for hours making minor changes just to make a 30 minute build.

AI has not concern about how long anything takes, in general, but it if it's just waiting for it to return, it won't get impatient.

America needs a corporate death penalty. Not for people, but for organizations. The people themselves certainly should be prevented from being an executive anywhere else, but yes, corporations should be allowed to be killed.

they're not doing it right _or_ they're doing it correctly.

We're sorta in the age of alchemy. Lots of cranks out there, but there are real recipes.

Oh dontbworry, youll be in the matrix soon enpugh

Humans need sleep though.

First, you can read about Sam Bankman-Fried; then you can say "oh, he's not _real_ effective altrusim...and do your backflips.

it's interesting how much this sounds like astroturf.

Just a magical mental gymnastics for someone who got the message that greed is bad, but wanted to continue being greedy.

I assume it was put out to get inference engines ready to do qwen4 models. For AMD halo, the Halgogen engine is the fastest i dound so fare

I've adopted open source projects and have been working exclusively in languages I have very little experience with: typescript and go.

I'm using local models, and they go slow enough that I have no trouble following along with what they're doing; but visually, both go and typescript, along with react native, make me puke. So I wouldn't be able to do this without AI.

I describe how to do it in my comment history, but it's basically a Super-TDD along with some custom engineering harness.

I don't want to say skill issue, but the same way you can give a chain saw to a teenager and one to a skill craftsman, well, AI can obviously create whatever you want it to do.

I think some of the variety is simply how fast SOTA models pump out garbage that you simply have to close your eyes because it's not sensible to just watch characters flow across the screen.

Almost all the coding I'm doing via AI is just faster than readable. But I can see the thinking traces and I stop to model when it's obvious it doesn't understand my intent, etc.

So I'm not doubting you created garbage. I'm just doubting that it's a product of soley AI use.

don't forget: tests also inform the agent on what the code is _supposed_ to do. So with the cycle, you end up with 3 different potentially robust ways to look at and understand how to extend.

Context then is: docs, code and tests. Rather than try to build some omniscient agent, the context is built where the agent needs it.

I'm working on local models; qwen3.8-Flash-Next seems to be passed to rubicon.

I'm working on javascript, and now I'm only doing this via typescript. I've successfully got this going:

1. Design a feature in plain language with the coding agen (opencode) and write a document for it.

2. Restart the context (or I use /compact to flush any errant details)

3. Pull the new plan into context and ask the agent to revise it follow Test Driven Development.

4. Depending on how big it is, the agent places it into multi stages, each with it's own document.

It then loops through the stages. It might be entirely based on the language you're using, but this loop seems strong enough.

Then when there's bugs, errors, anything, we update the doc, add more tests, then revise the code.

It's quite possible the harness you're using isn't setup properly. For me to do this locally, I had to hack on dynamic context pruning which I described here: https://news.ycombinator.com/item?id=49906637#49907641

It kinda looks more like safety will be a segmented product. They're already placing safety on the general public.

I think the conceptualization vs implementation is what you're arguing with. They won't put safety on anything they give to the military industrial complex. They'll sell them whatever they want, whenever they want, because those budgets are greater and the liability less.

yeah, to some extent. I've been pulling repos to play around but I've now got a hard fork of paseo; I ripped out anything related to github. I upgraded the relay with security features to prevent abuse. I'm in the process of adding the first "real" large feature update that'll let the agents work over the relay with one another which will let me add compute wherever I find it. In the process of adding a browser plugin that will let me pull up pages for context to work on whatever (I don't trust even agents for searching the web).

And it's quite fascinating. Still dont think there's trillions of TAM out there if Qwen3.8-Flash-Next runs fast enough on $3k (before memory cartel) pricing.

I've got basically a loop of docs, test (TDD) and code. Starting with and IMPLEMENT-<plan name>.md. I ask to revise as TDD, then loop.

Once qwen3.8-flash-next showed up, it cañ go "forever" with dynamic context pruning.

It's fascinating for local coding.

Interesting they recommended high end software without considering quant 4 or 8 and still used A3B which should give good throughput on cheap hardware.

If they can follow Qwen3.8-Flash-Next, the could draft off the huge reduction in VRAM requirements.

What? I thought graphene was a graphql python: https://graphene-python.org/

Annnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnyways.

I think people with twitter accounts are the...sus