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

Grok 4.3

docs.x.ai

Post reply on HN
Print view View original

361–370 of 608 posts

Re: Grok 4.3

#361

Post by aembleton »

alex1138 wrote: post #346
aembleton wrote: post #135

Earlier quoted context omitted.

I've tried Grok, Gemini and ChatGPT. There have been 2 times now where Gemini and ChatGPT confidently gave me an incorrect answer whereas Grok was correct. I'm now paying for Grok Lite or whatever it is $10 plan. The first question was around setting up timers for a Fox ESS battery in Home Assistant and disconnecting Fox ESS from the cloud. The second was around cornering speed in Sunnypilot and Frogpilot. Somewhat n…

Hey, have you used Claude much? What are your experiences with it

No, I've not tried Claude.

Re: Grok 4.3

#362

Post by niek_pas »

coreyh14444 wrote: post #88
tornikeo wrote: post #30

So, we have: - claude for corps and gov - codex for devs - grok for what, roleplay, racism? Those are the two things I've ever heard grok associated with around me.

If you need to ask about what people on Twitter are talking about, Grok is really good for that obviously. I use it all the time for "what are the cool kids on twitter saying is the best tiling window manager these days" or whatever. Also, if you have a question that's borderline shady, Grok will often deliver. "Can you find a grey market Windows license site for me" etc.

> If you need to ask about what people on Twitter are talking about, Grok is really good for that obviously.

Isn't that why OP was asking about racism?

Re: Grok 4.3

#364

Post by jquery »

HarHarVeryFunny wrote: post #243
artdigital wrote: post #17

Grok is my favorite model for chatting, and my favorite voice mode. It seems to be the only voice mode that isn't routing to a extremely cheap model (like Haiku), and has been the highest quality out of all the frontier ones. When you subscribe to SuperGrok you can also create a "council" of agents, each with their own system prompt and when you ask something, they will all get asked in parallel to come to a conclusi…

The Gemini app voice mode uses one of their more recent models (and not some gimped small one), and is very capable. The personality is also fine, much more natural than the Gemini web chat, with my only complaint being it's insistence on suggesting a "next step" which seems to he something that they all do. I'm not sure if the "next step" is just to drive cost up for you (but makes no sense for free version), or bec…

The “next step” is in the system prompt, not the model. Gemini leaked part of its system prompt to me a few days ago, and there was something in there encouraging it to ask the user what they wanted to do next at the end of its response. Something about “give the user 1 or 2 options for follow up”.

I honestly find it rather annoying, but Gemini has stopped doing it to me for the most part, so maybe they’re trying out a new system prompt.

Re: Grok 4.3

#365

Post by goshx »

GorbachevyChase wrote: post #352
tornikeo wrote: post #30

So, we have: - claude for corps and gov - codex for devs - grok for what, roleplay, racism? Those are the two things I've ever heard grok associated with around me.

I know it’s really important to write and vocalize one’s alignment with the values of the day, but I don’t think language models being structurally incapable of offending your favorite race/ethnicity/caste should be an objective of AI labs. Language models are just systems and I’m not sure why we think users are not responsible for how they use their outputs. For the same reasons, I don’t dismiss the utility pens as…

> but I don’t think language models being structurally incapable of offending your favorite race/ethnicity/caste should be an objective of AI labs.

The opposite should not be an objective either, and Elon has been very openly manipulating what grok says.

Re: Grok 4.3

#366

Post by dgacmu »

gigatexal wrote: post #262
gigatexal wrote: post #116

How do the grok models fare in coding challenges to say gpt 5.5 and opus 4.6/4.7? I hate giving Elon any money. The man is a net negative to society but … if the models are objectively better then logically I must no?

All the downvotes are from Elon Stan’s. Think on your sins. ;-)

Oh, I dunno - I haven't downvoted it, but if I did, it would be for the idea that you "have to" give money to someone you don't want to just for a slight improvement. That's garbage. You don't have to. It's okay--no, it's _good_--to give your ethics a role in your decisionmaking.

Re: Grok 4.3

#367

Post by FeloniousHam »

sundarurfriend wrote: post #27

As an English-as-second-language speaker and writer, one thing Grok really shines at is capturing the tone and level of "formality" of a piece of text and the replicating it correctly. It seems to understand the little human subtleties of language in a way the other major providers don't. Chatgpt goes overly stiff and formal sounding, or ends up in a weird "aye guvnor" type informal language (Claude is sometimes bett…

I only use Grok through the "Gork" personality in the Tesla, but find its responses to be very realistic, often genuinely funny, and occasionally useful.

Re: Grok 4.3

#368

Post by Scroll_Swe »

SecretDreams wrote: post #358
Scroll_Swe wrote: post #350

Earlier quoted context omitted.

I am allowed to make accounts? You are just doing driveby "Elon bad" comments. Don't worry, I am an adult and intend to stay and better the community. As I have before. Do better next time please.

> Don't worry, I am an adult and intend to stay and better the community. Woof, glad to hear that. I was losing sleep before you clarified this one. Your first comment is effectively "the ends justified the means". I think this is a perspective more easily held when your own life isn't impacted by "the means", but does benefit from "the ends". Life's got plenty of nuance - we don't need to lose our humanity at every…

>Your first comment is effectively "the ends justified the means".

Yes? Welcome to the real world. The Nazis developed technologies that Western Europe, USA and the Soviet Union all wanted. In your view what should the US have done? Let the Soviets poach them all up and get better at tech and maybe take over Europe even more?

>I think this is a perspective more easily held when your own life isn't impacted by "the means"

I can say the same to you. I have seen the rapid decline of my country, Sweden, directly due to the 2015 migration crisis and before. So we very much are directly impacted, thank you.

>Life's got plenty of nuance - we don't need to lose our humanity at every opportunity for an incremental technological gain that would eventually come either way.

This is a very naive view that I am surprised to see on HN.

Would Linux have "just happened anyway" without Linus Torvalds? Would Windows have happened without Bill Gates? Facebook without Mark? Clean sewage without Joseph Bazalgette? Mobile X-Rays without Marie Curie? This is in reaction to your Werner Van Braun comment. Do you really think the USA set him to make rockets and engines because he was just a random engineer? No, some people are truly geniuses, and their one impact can matter.

Some societies are just better than others. You sit in (probably) the USA or western world, in probably a nice apartment or house willing to say screw it all all the good things will just materialize and happen by itself... I do too but I am not so naive. We have fought for our society.

Re: Grok 4.3

#369

Post by Eliezer »

base698 wrote: post #308
artdigital wrote: post #17

Grok is my favorite model for chatting, and my favorite voice mode. It seems to be the only voice mode that isn't routing to a extremely cheap model (like Haiku), and has been the highest quality out of all the frontier ones. When you subscribe to SuperGrok you can also create a "council" of agents, each with their own system prompt and when you ask something, they will all get asked in parallel to come to a conclusi…

Starting to like the lack of memory. Claude remembers I have a grill and will interject in conversations about how maybe this thing would go well with BBQ when it's unrelated or just also about food.

You can turn that off in settings.

Re: Grok 4.3

#370

Post by sheepscreek »

I’m surprised no one is commenting on how cheap this is compared to Opus 4.x and GPT-5.5.

$1.25 / $2.50 for every M input and output tokens.

Is this is a smaller less powerful model? What am I missing?

Post reply on HN