cyanydeez

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

It'll merely generate hyper local bots that generate hyper local slop. The media landscape is downhill.

it'll basically be scam vs scam if that's every what happens.

I'm running Qwen3.8-Flash-Next; other than speed on a 395+, it does most things that are properly planned out.

I can't believe the TAM requires more than it at a 2x speed up. OpenAI, Anthropic built models whose only purpose now is things like research and defense.

And by defense, obviously, in America, we mean war. killing, etc.

AI and Police have essentially the same journalists who, in lieu of any research or fact checking, just report verbatim their press releases and interviews.

eventually though, resimulations will never to revolve around trying to inject bad context into the the stream and try to distract them.

I think, "contexting" is apropos.

I relate a lot to what they do. Find words, alignment and suss out follow ups, ons, and outs to the next reasonable conclusion.

Then use that context to bootstrap the next because if you build a powerful conclusion than can reverse itself into its evidentiary context, then every next context step can update its priors.

And so on the turtles flow where like an LLM, THE start of the context disappears over the horizon, but as long as im contexting in disinterested chunks of equal quality, then its not a problem.

But while internal tobeach context you can find reason, as a requisite building block like falling tetris pieces, the whole isnt the sum of its parts.

There's two types of cares:

1. People like other people.

2. Businesses need to sell product

The internet mixes those people, and an Agent basically pushes the signal to noise ratio that businesses have relied on the intenet to basically zero.

If the internet just allowed indescriminate traffic, neither #1 nor #2 survives, and while it's interesting to think the value is, it certainly isn't anything we understand.

Maybe you think the value will still exist, but some how agents will replace all value with equivelents. That's an argument, but I don't think it will.

I assume most people have see the photos of various "far east" people sitting at a bench with an array of 100 phones.

This predates AI as a _capitalism_ problem.

I've got a plugin in development that'll do the same: via an extension, connect to a standard coding bot, so it can drive.

It can be used for testing software and using it as a human support.

But everyone tells us how valuable the dark fiber build out during the dotcom bust was.

Not nothing grift and probably An endorsement for the largest grift.

That didnt work against walmart. Fast food might be more resilient but once the AI lube and economic chaos commences, itll just be a brand behind a pinkslime wholesaler.

they've been basically building their own PC universe. They are not specifically trying to compete with America. They're trying to disown any reliance on America.

While Trump and Business minds of America focus on pumping and dumping our stock market, they're 10 to 20 years out on what they want.

It's fucking myopic to think China cares two shits about America.

Oracle just sent a force majeur to their data center in texas essentially telling them they can't expect to get paid for several years...

And you're trying to say someone should go out and invest 5 years, multiple billions in investment to catch up to today memory prices?

You arn't paying attention.

I mean, we can assume the people who make the memory love getting huge prices for it. But beyond that, I just dont see why someone who invest several multi billion dollars to squeeze into a potential window that may or may not last 3 years. Especially with how volatile the whole AI bubble is.

It also ignores the giant CAPEX and OPEX required for any competition. This isn't banana stands or book publishing, or whatever.

These are billion dollar+ funded operations that take multi-years just to see if you can compete at the levels required.

All these comments show up every time, like there's a memory faerie land where you just put on your memory faerie hat and walla! Memory!

So bizarre.

I get that you have no idea. That's all.