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

341–350 of 608 posts

Re: Grok 4.3

#341

Post by pdimitar »

microtherion wrote: post #338
pdimitar wrote: post #306

Earlier quoted context omitted.

I've seen this expressed as a concern even from one of my colleagues. My retort was: "English is not my native language and LLMs taught me quite a few very useful formalisms that do land well for people and they change their attitude towards you to be more respectful afterwards. It also showed me how to frame and reframe certain arguments. I agree sounding like an LLM is kind of sad but I am getting a lot of educatio…

It's impressive that you've even managed to use an em-dash in spoken language. /s

I did spot the /s but it's not relevant: I use two normal dashes actually. :)

Re: Grok 4.3

#342

Post by Scroll_Swe »

AntiUSAbah wrote: post #248
xiphias2 wrote: post #197

Earlier quoted context omitted.

Sure, then good like paying twice as much for the next Opus / Codex models. Margins are going up for the 2 frontier model providers like crazy, and I don't expect it to go down more, I think we have seen the cheapest token prices already.

We don't need Musk for this. There is plenty of Chinamodels, Mistral and co.

Mistral is just not as good, saying this as a European, sadly. I support them and would like to see them get better in their models, for chat especially as that is what I use. Dont use any CC, APIs etc.

I avoid using and buying Chinese things due to the country. That is my view. They will turn on us too.

Re: Grok 4.3

#343

Post by kccqzy »

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…

This is more of a user preference. When I want to be informed my default is that chat bots should imitate the tone of Wikipedia. Not informal, but somewhat academic and in-depth. I don’t like it when chat bots explain things like an average human without pedagogical training: meandering, in the wrong order, and often having to repeat themselves.

Re: Grok 4.3

#344

Post by SecretDreams »

Scroll_Swe wrote: post #339
SecretDreams wrote: post #177

Earlier quoted context omitted.

No point in even trying to have close to a sensible discussion on this topic here. Musk-related posts seem to consistently get brigaded by his acolytes or bots. That and many HN users seem completely comfortable separating morality for what little progress "only Musk" can offer humanity, a la Wernher von Braun.

[flagged]

Accounts like this make me feel bad for the mod team.

Re: Grok 4.3

#345

Post by dmix »

vorticalbox wrote: post #333
sudb wrote: post #57

Earlier quoted context omitted.

So interestingly, I know of at least one application in a charity that deals with trafficking where grok was happy to do one-shot classification tasks where all other models refused to cooperate. I think there's a surprising number of actually useful applications in this sort of grey area for a slightly-less guardrailed, near-frontier model (also the grok-fast models are cheap!).

I am software dev and i was doing a security check on my own application (work) I was running in localhost and gave it access to the code. every single model refused to attempt to run any sort of test to check if it was a n issue other than grok.

You couldn't even ask Claude how CopyFail worked. Even more general questions around it kept getting rejected.

Re: Grok 4.3

#346

Post by alex1138 »

aembleton wrote: post #135
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'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

Re: Grok 4.3

#347

Post by bilsbie »

Grok has become my go to search engine lately. I think it’s the only AI with access to x posts and beyond that it seems to generally be more “searchy” than other LLM’s.

Re: Grok 4.3

#348

Post by Scroll_Swe »

AntiUSAbah wrote: post #235
NotGMan wrote: post #182

Earlier quoted context omitted.

[flagged]

You are smart enought to post on hn but not smart enough to have an argument? Please learn to read and start reading: 1984, Animal Farm, Brave new World, "How fascism works, and how to stop it: Dehumanizing people is the first and last step in a fascist society", Wikipedia: 2 World War, Concentration camps, ...

And you should read up on the Soviet system, the failure of central planning, their occupation of Germany (Eastern Germany vs West Germany)

The holodomor (Ukraine genocide, yes a real one not a pretend Gaza one)

Read on the current Ukraine war, do you even support it?

Read on the Gulag system, Concentration camps really, so your side is not better :)

Stalins mass purges and deportations. No free speech, press, assembly, one party state rule. You want this?

Read up on Chernobyl, the cover up.

Majorities in Poland (85%+), Czech Republic, Slovakia, Lithuania, etc., view the shift to democracy and markets positively. Living standards, education, and opportunities improved. Ukrainians overwhelmingly reject it post-independence and especially after Russian aggression. Baltics treat Soviet era as occupation, not legitimate rule.

Because I suspect you are a socialist. Not in the sense of like me in Sweden, but an actual tankie one.

Re: Grok 4.3

#349

Post by dmix »

vrganj wrote: post #69
simianwords wrote: post #67

Earlier quoted context omitted.

[flagged]

How could MechaHitler possibly be far right...

MechaHitler was the result of a single line prompt change that was publicly available on Github, they reverted it pretty quickly. Much like the GPT Gremlin stuff the change was relatively innocuous system prompt but had larger implications.

Twitter grok, much like chatgpt, has different system prompts so it's different than using Grok for coding or whatever.

Re: Grok 4.3

#350

Post by Scroll_Swe »

SecretDreams wrote: post #344
Scroll_Swe wrote: post #339

Earlier quoted context omitted.

[flagged]

Accounts like this make me feel bad for the mod team.

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.

Post reply on HN