I probably have the same strix halo box as you. It's slow, although mostly tolerable, but even 128 GB isn't enough to run good models. Where that leaves us is giving money to somebody to get access to frontier models. I don't like any of those guys either, but some appear worse than others. FWIW, I mostly use Anthropic models. And CCP and their distilled models notwithstanding, at least they release open weight models at a lower cost. It's not like any American company can claim the higher ground these days anyway, especially when they trained their models on pirated content and trash our neighborhoods with their datacenters.

Yes, ethically Elon ranks lowest based on the past 5 years of questionable decisions, like uploading your entire codebase to their server without consent.

Elon is directly responsible for Grok becoming self-titled “MechaHitler” which the other three haven’t come close to matching yet.

For many people, yes. That’s how far down the Elon Musk morality bar is.

Elon would be in prison for SEC violations if the current administration hadn’t been elected, and that’s only the tip of the iceberg with that guy.

Paying people to vote is interfering amigo.

Remember when he got hired by the federal government and walked away with a ton of private data?

I think you are confusing the words interfere and influence.

Every accusation is a confession...

There's a big difference between quiet donations to a PAC - not that that's good either - and what Elon did. He literally paid for votes, likely in violation of the law. He poured more money into U.S. elections than anyone has before. He and Trump both made strange, cryptic statements about Elon's role in Pennsylvania with the voting machines that has caused people to reasonably wonder if they somehow manipulated the election. Whether he did or not, the innuendo alone is not ok. Then he did what he did in Germany. Don't even get me started on DOGE or his Starlink shenanigans in Ukraine.

That's before we even start talking about the models themselves. He claims to want "unbiased" models, but he very clearly has a distorted view of the world and has repeatedly demonstrated a desire and willingness to bend the world to his will. I don't want to use a model that is so obviously suspect. Not to mention, his models repeatedly produce racist, Nazi-like propaganda.

IMO, he is, at best, a clueless amateur masquerading as an expert and running into problems a more careful person manages to mostly avoid. At worst... well, you get the picture.

"Everyone's doing it" presented with no evidence is just you trying to make yourself feel better for: - using from - driving a Tesla - voting for Trump

It's a really, really easy line to draw in the sand: don't support openly corrupt individuals.

It's absolutely true there's money in politics. To call all money in politics equally corrupt because Bernie got a dollar to have dinner with someone vs Elon effectively directly buying votes....

A complete lack of nuance here. And I wouldn't be surprised if corporations / super rich WANT you to think like that. The more defeatist the mentality becomes the more we just accept whatever they do next.

It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. As an example, instead of sandboxing and simply verifying output artifacts they manually read and approve edits, suggest different code patterns, and manually approved shell commands. On the flip side it's not as good as fable when you need a relatively complex multi step thing done.

But in my experience, the overall productivity ends up similar, give you are willing to work with it in that way.

The grok build TUI harness is excellent and I really enjoyed using it.

For debugging and such I found it pretty much the same as other models.

Fable's taste in software abstraction and project planning in greenfield setups[1] is unmatched in my experience. Sol is OK. My primary use is launching tens of experiments that have to smartly use a limited pool of GPUs.

I use fable to start off the experiments, decide checkpoints, gpu alloc, where to sacrifice precision for performance, and then grok4.5 to iterate, tune, debug, eval, etc, within the abstraction and setup that fable initiated. I have fable write simple scripts that are then wrapped in skills for grok to use. Speed for that loop is extremely important for me, since I also apply human judgement there and I don't like waiting for model output.

I have tried Deepseek and such for the inner agent, but I desperately need multi-modal. Otherwise it's OK, but it tends to use tools less and rambles on and tries to reason with limited information and gets things wrong. Probably a relative la k of tool use posttraining. Gemini flash limits in google ai pro are too low for me to use to compare.

I use anthropic and openais models through grants and so can't compare subscription plan token budgets, but supergrok's budgets are satisfactory.

[1] aside, I have not yet met a model that continues off of a human codebase and actually follows the patterns reliably long term. Eventually it's all slop.

It's much faster, so if you're not doing something cutting-edge, or you're doing the planning yourself and just using the LLM for implementation, the speed benefit outweighs the extra smarts of Fable/Opus5/Sol.

It really does. I felt like I could have spent $1000+ api token on claude for the amount of work on my $30 grok subscription.

For me it helps that back when xAI was the new hotness, after reading HN comments constantly advertising the free Grok credits they were giving out each month for developers with data sharing enabled, I eventually set aside my personal distaste figuring I might as well take advantage for Cline/Roo Code.

I opened a developer API account, loaded 5 dollars and got the free $100s of credits for the month. Like two weeks later, xAI announced they were shutting down the subsidized credits entirely lol. Didn’t even get a full month out of it, and closed my account entirely since I sure wasn’t ever going to put another penny of my own money in.

So my personal lesson was to ignore any hype about the latest “crazy value / unbeatable / free / subsidized X, Y or Z” from anything xAI/Elon adjacent in the future.

These days I get more than enough personal usage from Codex + OpenCode Go to put up with yet another xAI/Cursor offer treadmill, especially if it involves installing new tooling to get it.

I don’t like what is happening in my country, Elon is a huge part of that and I don’t want to reward it. I’m not a fanatic, but if all other things are equal I can certainly factor social responsibility into the equation. Fuck that rage baiting xenophobic nazi-salute throwing asshole. [edit spelling]

Chinese models are open, Grok is not.

macOS Codex app is my main agent (its very polished). When it makes changes or code scans i ask it to run claude -p plus cursor-cli plus grok cli for double checking. This way bias of one model can be overruled by quorum.

Yeah, sounds a bit like a selection bias, i.e. the people who managed to survive the firings by DOGE and the current admin are the kind of people who might prefer Grok.