Live data from Hacker News

Grok 4.3

docs.x.ai

581–590 of 608 posts

Re: Grok 4.3

#581

Earlier quoted context omitted.

Did you do legal filings with it after doing your taxes? Oh my.

what do you mean?

It was a joke about people relying on AI and it doing absolutely terrible things.

Coding is an interesting area -- it can code, then compile to see if that part worked, then test to see if more worked.

With taxes, it sets things up and the review phase is the IRS fining you.

Re: Grok 4.3

#582

Earlier quoted context omitted.

She's 50 years old has a doctorate in pharmacy and has worked as a hospital pharmacist for two decades. I don't say this as a "gotcha", but more that even with all that experience she still finds it beneficial and helpful.

That makes it more sad, to me. Someone with those credentials should be able to communicate with their colleagues effectively. I wonder if she used to be able to. It appears Hacker News disagrees that social skills are valuable skills. Mea culpa, I should have guessed.

There's something ironic about complaining about other people's social skill while you couldn't be bothered to make a point without sounding dismissive and condescending.

Re: Grok 4.3

#583
post #559

Earlier quoted context omitted.

Interesting. I have not had this experience. I would like to learn more. Can you point me to any examples or domains where I might be able to replicate this?

I was asking questions about compiler techniques. Then when I got annoyed I started asking about experimental design. Both were very frustrating experiences once I started realizing how limited its responses were. Though yeah the edgelord-y style faded after I criticized it a couple times.

I'll take a look. Thank you!

Re: Grok 4.3

#584

Earlier quoted context omitted.

Luckily inference is cheap, and other providers offer efficient models. It’s only going to get better in the future.

Its not though, just because your favorite CEO or youtuber said it will, doesnt mean it will. Inference is not cheap, you have no idea what you're talking about. Every new chinese model has doubled their prices in the last two weeks

Kimi K2.6, the leading open-weights model, is $0.95 input / $4.00 output / $0.16 cache.

That’s about 1.45x more expensive than K2.5 from January.

It is around 5x cheaper than GPT 5.5.

Re: Grok 4.3

#585
post #414

Earlier quoted context omitted.

[flagged]

Do any of them argue for leftist positions? I am not aware. Please use actual argument instead of assertions and derailment.

I see. This is some sort of weird purity spiral, where no party is left wing unless they meet your arbitrary chronically online standards that no-one adheres to in real life. Touch grass dude.

Re: Grok 4.3

#586

Earlier quoted context omitted.

My searches have not turned up a result showing that Musk "claimed he had never corresponded with Epstein". Can you source this? If not, can you explain why you did not check it before you posted the inaccurate claim?

I misremembered. Mea culpa. He did NOT claim never to have corresponded with Epstein. Instead he claimed that Epstein asked him to go the island and he refused. The files show the opposite to be true. Still an absolutely enormous lie of the sort you would only tell if guilty. Here it is in his own words. See above for one of several examples in the files illustrating how very untrue it is. https://x.com/elonmusk/stat…

I looked into this long ago, and imo it doesn’t look as bad as you say.

Musk downplayed his correspondence and willingness to meet with Epstein to the point where you could argue Musk was lying, yes.

However, he did decline an invitation to the island in 2012/13, at first because Musk was looking for a party and thought this would be a peaceful island experience. Eventually Musk declined because of logistics.

Re: Grok 4.3

#587

Earlier quoted context omitted.

> Ashley Biden diaries Unless they contain allegations about Biden the president, or indeed other people then they are irellevent no? The point is, if someone is breaking the law, they should be in jail. This applies to Clinton, Biden, Trump, anyone. The point is the law is meant to be without fear or favour. The problem for us is that its been proven if you pour enough shit on the floor, you can get away with raping…

Obviously the intelligence material being gathered was too valuable.

I'm sorry you're gonna have to explain that, what intelligence and why was it valuable?

so valuable that only the press paid any money for it?

Re: Grok 4.3

#588

Earlier quoted context omitted.

Have you ever written a comment about how any of the other LLMs are editorializing in favor of the left, and how that's a problem? Because if you have, I'd love to see the evidence of your intellectual consistency. But something tells me you're just doing the same thing that you're calling out

> about how any of the other LLMs are editorializing in favor of the left I’m sorry come again now. Would you possibly have some examples of this

There’s tons you just need to spend a few minutes and look. Here’s one for you—black Nazis and Asian Vikings, oh my:

https://www.nytimes.com/2024/02/22/technology/google-gemini-...

Re: Grok 4.3

#589

Earlier quoted context omitted.

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…

I think the "next step" instruction is more about engagement than cost, basically giving the user some options to continue the chat. I always have had success by ending the prompt with "only reply with nothing else but the answer to the query in a precise way". This usually always works better than telling it to not ask leading questions etc but a straight up expectation of the answer format you need is an instructio…

I find that asking Gemini "just the answer, no follow up" etc works at best for one or two conversational turns, sometimes none!

The problem seems to be the way it in effect overweights the system prompt vs user input, so it quickly ignores things like this that conflict with the system prompt.

This is kind of a case of the bitter lesson - the conversational patterns of these models would be much more natural if they just let it learn them, and respond in a context appropriate way, rather than this crude system prompt way of forcing it to respond in the same way always, regardless of input or of how much the user tells it to shut up!

Re: Grok 4.3

#590
post #414

Earlier quoted context omitted.

Do any of them argue for leftist positions? I am not aware. Please use actual argument instead of assertions and derailment.

I see. This is some sort of weird purity spiral, where no party is left wing unless they meet your arbitrary chronically online standards that no-one adheres to in real life. Touch grass dude.

You still have not brought a single argument and continue your attempts at derailment.

It's okay to admit you were wrong.

Post reply on HN