Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grok 4 Fast now has 2M context window

docs.x.ai

Post reply on HN
Print view View original

171–180 of 328 posts

Re: Grok 4 Fast now has 2M context window

#171

Post by m-hodges »

nsoonhui wrote: post #101

It's a shame that the top comments are focusing more on Elon Musk, his personality and politics rather than the quality of the model per se. Speaking about Elon, regardless of what you think of him, he really does get things done, despite naysayers -- SpaceX, Tesla, Neuralink and even get Trump elected ( despite subsequent fallout) etc. Even Twitter is finding a second life by becoming a haven for the free speech adv…

> Even Twitter is finding a second life by becoming a haven for the free speech advocates and alternative views, much to the chagrin of MSMs because they now no longer have the monopoly on the "truth"

Of all the silly things to say about Musk and Twitter, the idea that “MSM” are upset about Twitter is among the silliest.

Re: Grok 4 Fast now has 2M context window

#173

Post by f311a »

danskeren wrote: post #60
Sherveen wrote: post #21

Earlier quoted context omitted.

[flagged]

I throw all my queries at Grok 4 Expert, GPT 5 Thinking and Opus 4.1 Extended Thinking.. for Golang it's been my experience that Grok produce the best results about 90% of the time as well. Some simple example: https://claude.ai/share/6d178173-cdf7-4e50-a467-73ee9f479d56 . https://chatgpt.com/share/69102735-46ac-8012-9cf0-0969585c86... . https://grok.com/share/bGVnYWN5LWNvcHk%3D_54b5f2f1-732e-4372... . I don't use Ge…

Not sure about Claude, but OpenAI models are pretty bad at Go for some reason. For example, they always want to replace the "new" style for-loop that uses range with the old syntax. This drives me nuts.

Re: Grok 4 Fast now has 2M context window

#174

Post by jasonvorhe »

galaxy_gas wrote: post #24
behnamoh wrote: 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 have try it a few times in Copilot as code fast 1 because it was advertised. It has never correctly done something so far. Maybe because it's the fast ver ?

Maybe you just used it wrong? I refactored a complicated code base, built exhaustive tests for a CLI app and I've been maintaining and building out several k8s clusters out of a mono repo using Cline + grok-code-fast-1 and it's been a breeze.

Re: Grok 4 Fast now has 2M context window

#175

Post by mg »

MallocVoidstar wrote: post #160
mg wrote: post #150

Earlier quoted context omitted.

If a model is not making use of the whole context window - shouldn't that be very noticeable when the prompt is code? For example when querying a model to refactor a piece of code - would that really work if it forgets about one part of the code while it refactors another part? I concatenate a lot of code files into a single prompt multiple times a day and ask LLMs to refactor them, implement features or review the c…

I don't think there are any up-to-date leaderboards, but models absolutely degrade in performance the more context they're dealing with. https://wandb.ai/byyoung3/ruler_eval/reports/How-to-evaluate... >Gpt-5-mini records 0.87 overall judge accuracy at 4k [context] and falls to 0.59 at 128k. And Llama 4 Scout claimed a 10 million token context window but in practice its performance on query tasks drops below 20% accur…

That makes me wonder if we could simply test this by letting the LLM add or multiply a long list of numbers?

Here is an experiment:

https://www.gnod.com/search/#q=%23%20Calcuate%20the%20below%...

The correct answer:

    Correct:    20,192,642.460942328
Here is what I got from different models on the first try:

    ChatGPT:    20,384,918.24
    Perplexity: 20,000,000
    Google:     25,167,098.4
    Mistral:    200,000,000
    Grok:       Timed out after 300s of thinking

Re: Grok 4 Fast now has 2M context window

#176

Post by testdelacc1 »

latexr wrote: post #169
nsoonhui wrote: post #101

It's a shame that the top comments are focusing more on Elon Musk, his personality and politics rather than the quality of the model per se. Speaking about Elon, regardless of what you think of him, he really does get things done, despite naysayers -- SpaceX, Tesla, Neuralink and even get Trump elected ( despite subsequent fallout) etc. Even Twitter is finding a second life by becoming a haven for the free speech adv…

[flagged]

[flagged]

Re: Grok 4 Fast now has 2M context window

#177

Post by TheOtherHobbes »

roman_soldier wrote: post #108
kburman wrote: post #62

Earlier quoted context omitted.

Not defending anyone, but by that logic, you shouldn’t be using any Chinese models either.

[flagged]

That's because they don't have links to far right organisations around the world, they aren't running a social media site that aggressively promotes hate speech, they're not attempting to foment civil war in countries like the UK, and they don't say rambling grandiose crazy shit about colonising Mars or having self-driving cars real soon now which is clearly insane, makes no sense to anyone rational, and has a long record of being exaggerated and wrong.

None of this is hyperbole. All of it is historically documented.

Re: Grok 4 Fast now has 2M context window

#178

Post by thecopy »

danskeren wrote: post #60
Sherveen wrote: post #21

Earlier quoted context omitted.

[flagged]

I throw all my queries at Grok 4 Expert, GPT 5 Thinking and Opus 4.1 Extended Thinking.. for Golang it's been my experience that Grok produce the best results about 90% of the time as well. Some simple example: https://claude.ai/share/6d178173-cdf7-4e50-a467-73ee9f479d56 . https://chatgpt.com/share/69102735-46ac-8012-9cf0-0969585c86... . https://grok.com/share/bGVnYWN5LWNvcHk%3D_54b5f2f1-732e-4372... . I don't use Ge…

Isn't Sonnet 4.5 stronger than Opus 4.1?

Re: Grok 4 Fast now has 2M context window

#179

Post by TheOtherHobbes »

oulipo2 wrote: post #157
ronsor wrote: post #48

This post really has no reason to be flagged. I know Elon is controversial, and I have a lot of gripes with his business practices myself, but this is literally just documentation for a frontier LLM. Can we stay on topic?

The politics of the owners IS the topic. It's being really naive (read: stupid) to think that this has no implication on society

You're literally handing over your code to a third party.

In fact AI is handing over the process of creating code - eventually all code - to a small number of third parties, who will have complete power over the world's IT infrastructure.

No wonder they have wildly inflated valuations. The potential to enforce authoritarian policies through opaque technology is unprecedented.

Post reply on HN