Earlier quoted context omitted.
[flagged]
You’re replying to the wrong comment.
[flagged]
Grok 4 Fast now has 2M context window
251–260 of 328 posts
Re: Grok 4 Fast now has 2M context window
#252I had a failed refactor with Codex recently and I am wondering if context window size is the cause.
For complex refactors, I use "max mode" in Cursor, which in my experience noticeably improves the AI's performance and makes it go for a lot longer before it starts to drift. I haven't looked into how it works exactly, but it works well if you don't mind the extra cost.
Had some bad experiences with max mode and the latest Claude spending significant time on writing worthless .md files rather than solving problems
Re: Grok 4 Fast now has 2M context window
#253Who 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…
Groks underrated honestly. If you have to market on X you need a sub anyway so it’s replaced casual questions/sort of questions I used to Google for me and I’m not seeing anything worse than ChatGPT and often it’s better. Much better at current events.
The video gen is actually really good fast and cheap for short videos.
Still use Claude and GPT5 for work tasks but I haven’t tried grok extensively for those
Re: Grok 4 Fast now has 2M context window
#254Earlier quoted context omitted.
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…
Since grok 4 fast got this answer correct so quickly, I decided to test more.
Tested this on the new hidden model of ChatGPT called Polaris Alpha: Answer: $20,192,642.460942336$
Current gpt-5 medium reasoning says: After confirming my calculations, the final product (P) should be (20,192,642.460942336)
Claude Sonnet 4.5 says: “29,596,175.95 or roughly 29.6 million”
Claude haiku 4.5 says: ≈20,185,903
GLM 4.6 says: 20,171,523.725593136
I’m going to try out Grok 4 fast on some coding tasks at this point to see if it can create functions properly. Design help is still best on GPT-5 at this exact moment.
Re: Grok 4 Fast now has 2M context window
#255Earlier quoted context omitted.
What models are better than Grok?
Sonnet-4 and onward, GPT-4 and onward
Saying “GPT-4” is dishonest, launch GPt4 was significantly better than anything devday downgrade, all the 4o nonsense etc.
In reality GPT really sucked from devday until 5 and it redeemed itself
Re: Grok 4 Fast now has 2M context window
#256Earlier quoted context omitted.
I can’t tell if this is serious or not. Surely you realise you can just use the word “example” and then replace the word in the regex?!
I think they would want a more optimized regex. Like a long list of swears, merged down into one pattern separated by tunnel characters, and with all common prefixes / suffixes combined for each group. That takes more than just replacing one word. Something like the output of the list-to-tree rust crate.
Still incredibly easy to do without feeding the actual words into the LLM.
Re: Grok 4 Fast now has 2M context window
#257It's funny how fast this post is flagged, lol. Have other LLMs or blunt ads got the same treatment on HN?
[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.
Re: Grok 4 Fast now has 2M context window
#258Earlier quoted context omitted.
[flagged]
But Tesla != Musk. He wasn't actually a founder, he bought his way in, and demanded that everyone agree he was a "founder". Not to mention the huge numbers of real scientists working over the decades to improve battery tech to the point where it was obvious that electric cars were going to be viable. We shouldn't praise Musk for taking credit for other people's work.
Doesn’t matter, every normie thinks he is so his influence impacts Tesla for better or worse.
Re: Grok 4 Fast now has 2M context window
#259What matter is not context or the recod token/s you get. But the quality for the model. And it seem Grok pushing the wrong metrics again, after launching fast.
Seems reductive. Some applications require higher context length or fast tokens/s. Consider it a multidimensional Pareto frontier you can optimize for.
It's not just that some absolutely require it, but a lot of applications hugely benefit from more context. A large part of LLM engineering for real world problems revolves around structuring the context and selectively providing the information needed while filtering out unneeded stuff. If you can just dump data into it without preprocessing, it saves a huge amount of development time.
Re: Grok 4 Fast now has 2M context window
#260Grok? Next…
I personally find grok better for certain tasks. It’s better than Gemini for images. Its better than the rest at crude jokes etc