Hacker News Reader

Comment by shevy-java | Hacker News Reader

[flagged]

Been very skeptical for awhile but decided to try it cause it was like $30 for 3 months or something. I cancelled my Claude subscription (still have codex), but been pretty impressed with the grok CLI. Nice TUI and seems intelligent thus far.

Really? I've used all of the models extensively and Grok doesn't even compare to the others. I can ask for a big task and it will say "Done!" like 3 minutes in, but it will have done just the least amount of work possible. I also notice "muskisms" leaking back in the results like "I'm not roasting your code". Completely unusable for me and not comparable to the other model providers.

Interesting, havn't noticed that. Mine will work for hours. Maybe i'm still in the "get them hooked" phase. Just started using it last week.

That is interesting, I've never been able to get it to successfully complete big tasks to any level of quality. For me the Anthropic models are by far the best at that, but the newer OpenAI models are starting to approach that quality. Grok always seemed like it was designed to write nasty tweets and the code quality I got from it matched that.

I'm considering switching as well, used the API to code with Grok via pi, was really pleasant whereas using Claude just gives me a cortisol spike

The only model I've found to beat it for coding (Python, Rust, Kotlin, PHP) and planning is Fable. What are you using it for?

I'm using it for coding and it's never approached the level of Opus for me. Sol is pretty good too.

I actually haven't used Sol yet. I'd love to hear what you use it for, and how it performs.

I think it's good for mid-sized tasks. It seems quick too. It just doesn't do as good of a job with large changes or architectural decisions as Opus imo.

When did you try it? Grok before 4.5 was way worse in my experience.

I don't remember the version exactly but maybe June/July timeframe? I tried it on maybe a half dozen projects with different types of asks as I was comparing models for my company at the time.

Grok 4.5 came out in mid July and is a huge leap forward. Not quite as good as Opus 5 for code in my experience, but better and more succinct for understanding human documents.

Yes. It’s one of the best coding models right now. Highly recommend.

Cursor is worth it because Grok 4.6 is around Opus 4.6 but you get much more usage with it than with Claude Code.

Yes, via a pre-existing Cursor contract that won’t be renewed (sans a Musk exile). I’ve also heard that GrokBot is surprising simple and usable.

We use it but limited to APIs. Their fast-think-2.0 model for voice conversations is a lot more natural than the openai realtime2.1

They have like a 5% market share. So in the big picture, almost no one uses Grok. But it's not nothing.

5% is a lot.

I'm not sure where you're getting accurate data from (I couldn't seem to find any that seemed trustworthy) but Anthropic and OpenAI, being the two big players, presumably take ~40% and 5% isn't that much of a disadvantage in a market where users can move rapidly.

Given the quality of the last couple Grok models, I'm sure their share is on the upswing as users make the switch.

recently i tried grok 4.6. and to me, it seems better than claude (opus). it follows the system prompt very accurately and remembers everything unlike claude (opus), it doesnt forget the system prompt during long conversations. but yes that depends on your purpose or approach to using AI

I use it in Cursor, recent versions are good for writing specs, code review, etc. Not good for UI design and broad research, though. Btw it does not have outage in Cursor now, it seems the infra path is different for XAI Grok and Cursor Grok.

I have a friend who uses it for pentesting since the cyber guardrails are mere suggestions. Can't imagine what kind of nasty sh*t this model has seen.

In AI Art scene people do use Grok. It‘s good.

I think there's a strong consensus that the idea of an "AI art scene" is a misnomer. There's an AI slop scene, and some of the prompters sure do call themselves artists.

Consensus among whom? AI is a tool, that can be used differently and AI art is well-recognized, admired and exhibited the same way as any other art forms.

Is someone selling their impressionist paintings today on a fair more an artist than someone who has put equivalent or more effort in creating prompts, references, final renders, image curation and postprocessing etc? The latter may at least have more audience.

>AI art is well-recognized

I disagree with this assertion. I don't think it's at all well-recognized, and in fact derided and shunned by the general public.

> Is someone selling their impressionist paintings today on a fair more an artist than someone who has put equivalent or more effort in creating prompts, references, final renders, image curation and postprocessing etc?

Emphatically, yes. Considering the latter is not an artist at all.

By that logic collages and photography aren't art. Composition of human ideas regardless of the tool or medium is itself art.

Please review the above comments. I have not made a single statement that leads to exluding either of those. My comments did not seek to define art, or the artistic process, only to exclude a specific category of media.

Well, that‘s your subjective opinion. In 1860s people like you rejected impressionism.

Meanwhile:

https://www.art-magazine.ai/program

note some nice venues in the list.

I wonder what provider they use at Tesla.

They also host Anthropic and OpenAI

Not OAI.

It has great web search, and is one of the best models on the AA-Omniscience Hallucination Rate benchmark (meaning it is really good at admitting it doesn't know something, rather than confidently bullshitting)

In terms of raw intelligence it's also good, Grok 4.6 benchmarks in the same league as Opus and Sol. xAI has lots of issues (not the least of which is being headed by Elon Musk), but their models are solid

It’s shame I’ll never use them. I’m sure the engineers are incredibly capable.

Really? If so, it's still subject to the whims of the main issue you pointed out.

I wouldn't trust that piece of trash if you paid me good money.

I don't use Grok either.

And why use it when there are many equivalent/better alternatives.

What is this opinion even based on? Grok 4.6 is the best model in terms of intelligence per token. And 4.6 heavy is almost on par with the SOTA models.

4.7 in two weeks might be the new SOTA.

It's my favorite chat box for general use. I used to cross post my questions to Opus/Fable and GPT Sol via Open Router but these days I just use Grok. I prefer its style, it's very good at searching and referencing sources. Doesn't make you feel like a genius (Gemini) but also isn't condescending (like Claude).

I like grok 4.6 more than any anthropic or claude model. I use it in cursor for work, and grok cli for normal os operations/installations/troubleshooting. I also use grok on my phone for normal questions in the supermarket etc.

I've yet to organically run into anyone who regularly uses Grok for coding. I'm sure they're out there, but what I hear with my own ears tells me that Grok is a relatively small slice of the market.

In my sphere of colleagues, it seems like at least 90% are using Claude exclusively and the remaining 10% are using some amount of Codex. Granted, my work only pays for Claude, but even so, nobody is talking favorably about Grok or begging our work to pay for it.

In my private life, the only people I know using Grok for non-work items are, frankly, conservatives who took the Elon pill. They see it as more truthful than ChatGPT. But they're pretty much using it for answers and not to produce anything.

That’s mostly because Grok only became good enough to be worth using about a couple of months ago when Grok 4.5 was released.

I feel confident enough that I can plan with fable or GPT5.6 and then hand it off to Grok to implement for certain complex tasks. If it’s a simple task, I can go straight to Grok.

I like mixing and matching to take advantage of these LLM subsidies and also trying to figure out each of its strengths.

All Cursor users as they have very high usage limits for their first party models ie Grok and Composer, even higher than Codex, much less Claude Code.

Reply on news.ycombinator.com