Live data from Hacker News

Grok 4 Fast now has 2M context window

docs.x.ai

291–300 of 328 posts

Re: Grok 4 Fast now has 2M context window

#291

Earlier quoted context omitted.

[flagged]

Nothing you posted (from an almost two year old article btw) in anyway refutes the prior comment. Grok is significantly the most biased. Did you sleep through its continuous insertion of made up stuff about south africa? This is the same person who is trying to re-write an entire encyclopedia because facts aren't biased enough. A group has created an alternate reality echo chamber, and the more reality doesn't match…

It takes a lot of chutzpah to accuse people of "re-writing ... facts & history" while peddling AI (and movies and TV shows) that change the ethnicities of historical figures.

Re: Grok 4 Fast now has 2M context window

#292
post #229
post #193

Earlier quoted context omitted.

Grok's biggest feature is that unlike all the other premier models (yes I know about ChatGPT's new adult mode), it hasn't been lobotomized by censoring.

I am amazed people actually believe this Grok is the most biased of the lot, and they’re not even trying to hide it particularly well

Bias is not the same as censoring.

Censoring is "I'm afraid I can't let you do that, Dave".

Bias is "actually, Elon Musk waved to the crowd."

Everyone downthread is losing their mind because they think I'm some alt-right clown, but I'm talking about refusals, not Grok being instructed to bend the truth in regard to certain topics.

Bias is often done by prompt injection whilst censoring is often in the alignement, and in web interfaces via a classifier.

Re: Grok 4 Fast now has 2M context window

#294

Earlier quoted context omitted.

[flagged]

I believe those people are eager to discuss Musk. The people suppressing Musk discussion are the forces backing him, who are out here working to suppress inconvenient speakings.

I honestly can't compute the logic of your statement.

Re: Grok 4 Fast now has 2M context window

#295
post #272

Earlier quoted context omitted.

I thought the number of tokens per second doesn't matter until I used Grok Code Fast. I realized that it makes a huge difference. If it take more than 30s to run, I lose focus, and look at something else. I end up being a lot less productive. It also opens up the possibility to automate a lot more simple tasks. I would def recommend people try fast models

If you are single tasking, speed matters to an extent. You need to still be able to read/skim the output and evaluate its quality. The productive people I know use git worktrees and are multi-tasking. The optimal workflow is when you can supply it one or more commands[1] that the model can run to validate/get feedback on its own. Think of it like RLHF for the LLM, they are getting feedback albeit not from you, which…

Hmm. I run maybe 3 work streams max in parallel and struggle to keep up with the context switching. I have some level of skepticism that your colleagues are amazingly better and do 4 and produce quality code at a faster rate than 1 or 2 work streams in wall clock time. I consider a workstream to be disparate features or bugs that are unrelated and require attention. Running 8 agents in parallel that are all doing the same thing is of course trivial nowadays but that in of itself is what I would consider a single threaded workstream.

Re: Grok 4 Fast now has 2M context window

#296

Earlier quoted context omitted.

If you are single tasking, speed matters to an extent. You need to still be able to read/skim the output and evaluate its quality. The productive people I know use git worktrees and are multi-tasking. The optimal workflow is when you can supply it one or more commands[1] that the model can run to validate/get feedback on its own. Think of it like RLHF for the LLM, they are getting feedback albeit not from you, which…

Hmm. I run maybe 3 work streams max in parallel and struggle to keep up with the context switching. I have some level of skepticism that your colleagues are amazingly better and do 4 and produce quality code at a faster rate than 1 or 2 work streams in wall clock time. I consider a workstream to be disparate features or bugs that are unrelated and require attention. Running 8 agents in parallel that are all doing the…

We have similar definition of streams, but It depends on a lot of things from your tooling/ language , stack etc.

if your builds take a fair bit of time (incremental builds may not work in worktree first time) or you are working on a item that has high latency feedback like e2e suite that runs on a actual browser etc.

Prompt styles also influences this. I like to make fairly detailed prompt that cover a lot of the nuances upfront and spend 10-15 or more writing it. I find that when I do that it takes longer, but I only give simple feedback during the run itself freeing me to go next item. Some people prefer chat style approach, you cannot keep lot of threads in mind if chatting.

Model and cli client choice matters , on average codex is slower than sonnet 4.5 . Within each family if you enable thinking or use the high reasoning model it can be slower as well.

Finally not all tasks are equal, I like to mix some complex and simpler ones or add some dev ex or a refactor that requires lower attention budget with features that require more.

Having said that, while I don’t know 10x type developers. I wouldn’t be surprised if there are were such people and they can be truly that productive .

The analogy I think of is chess. Maybe I can play 2-3 games in parallel reasonably well, but there are professional players who can play dozens of games blindfolded and win all of them.

Re: Grok 4 Fast now has 2M context window

#297
post #6

Who here actually uses Grok? It's sad to see Elon's arc but when he doubled down on some of his political ideas he had it coming with the Tesla sales going down and x.ai not taken seriously. I've always tried to remain apolitical and unbiased but it's hard to overlook who's behind a technology you wanna buy. Not that sama and others are saints either, it's just Elon's very obvious and vocal about it. It's a shame, re…

I won't go near anything Elon touches because of this. He's a clown.

Re: Grok 4 Fast now has 2M context window

#298
I started with ChatGPT, then moved on to Claude, and then discovered Grok. But now I've stopped paying for any of them. Claude edged out ChatGPT in quality, while Grok stood out with its generous usage limits. That all changed, though, once they rolled out the agent system and RLHF. Suddenly, the model slowed to a crawl, veering off on wrong paths and getting lost in its own reasoning. Those endless, super-annoying RLHF popups didn't help either.

My theory? They were scrambling for a competitive edge and were willing to swallow some short-term pain. Plus, it feels like they shifted focus away from keeping coders deeply in the loop.

In the end, we vote with our wallets—if it doesn't click, just walk away. I still dip into Grok, but only the free tier: Grok 4's fast mode for tackling planning and first generation, and then Qwen Coder for the code editing and clerical tasks. The latest version of grok hold up about as well as the old Grok 3, just with way more steps...

Re: Grok 4 Fast now has 2M context window

#299
post #246

Earlier quoted context omitted.

[flagged]

Oh the hubris.

Well, it's kind of a tautology, isn't it? Conservatism always loses in the end, for better or worse, simply because the world and everything in it undergoes change over time.

Re: Grok 4 Fast now has 2M context window

#300

Earlier quoted context omitted.

Nothing you posted (from an almost two year old article btw) in anyway refutes the prior comment. Grok is significantly the most biased. Did you sleep through its continuous insertion of made up stuff about south africa? This is the same person who is trying to re-write an entire encyclopedia because facts aren't biased enough. A group has created an alternate reality echo chamber, and the more reality doesn't match…

It takes a lot of chutzpah to accuse people of "re-writing ... facts & history" while peddling AI (and movies and TV shows) that change the ethnicities of historical figures.

Two years is an eternity in this business. Got anything newer than that?
Post reply on HN