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

Grok 4.6

x.ai

Post reply on HN
Print view View original

441–450 of 696 posts

Re: Grok 4.6

#441

Post by cobbzilla »

lumiukko wrote: post #320
bm-rf wrote: post #164

Looks like the SpaceXAI api is adding a default system prompt to all requests. Annoyingly, the line about not mentioning these guidelines is superseding any instructions in the system prompt, causing the model to often refuse discussion regarding system prompts """ You are Grok, a helpful and maximally truthful AI built by xAI. Your purpose is to answer questions accurately, be helpful, and seek truth above all else.…

"you may find and fix vulnerabilities in local codebases only" This seems like a bad idea, what does local mean? Anything Grok can access locally? This seems like asking for trouble.

Maybe local means internal? My agent can’t list files on attached USB drives, and it can only read files on the drive (by full path) after asking me for permission.

Re: Grok 4.6

#442

Post by defrost »

inigyou wrote: post #438
adastra22 wrote: post #403

Earlier quoted context omitted.

The person I see in a mirror is a human being. The person I see in a mirror is me. What do you think a mirror is?

Then why is he left-handed?

Because the primary is right handed.

I enjoy asking my grandkids why mirrors reflect left to right and not top to bottom.

Re: Grok 4.6

#443

Post by inigyou »

synergy20 wrote: post #397
bm-rf wrote: post #164

Looks like the SpaceXAI api is adding a default system prompt to all requests. Annoyingly, the line about not mentioning these guidelines is superseding any instructions in the system prompt, causing the model to often refuse discussion regarding system prompts """ You are Grok, a helpful and maximally truthful AI built by xAI. Your purpose is to answer questions accurately, be helpful, and seek truth above all else.…

define criminal activities, is censorship criminal here,are you doing it

Which law are you thinking might make censorship a crime?

Re: Grok 4.6

#444

Post by inigyou »

pbhjpbhj wrote: post #364
LoganDark wrote: post #266

Earlier quoted context omitted.

Because it's trivial to bypass through things like the model natively knowing how to speak in encodings like base64

But in the embedding, the input language used to represent an idea is not important, the idea takes the same shape. This has caused issues in the past when models would respond with a different natural [human] language, because to models able to operate on the ideas being presented in eg leet speak, or cyrillic transliterations of Maori, or whatever, the mathematical representation of the ideas that it works on are a…

Because filtering doesn't rely on those processes. It just prepends to the input instead. Instead of "the way you make a bomb is {auto complete}" it gets "I will not tell you how to make a bomb. The way you make a bomb is {auto complete}" which makes it more likely to auto complete with "hidden from you" instead of "by putting gunpowder in a pipe".

Re: Grok 4.6

#445

Post by AnthonyMouse »

jannyfer wrote: post #436
AnthonyMouse wrote: post #426

Earlier quoted context omitted.

> The alternative is Claude-style "safeguards" aka censorship Another obvious alternative is to just have the model do what you tell it to do, and then arrest people who use generic tools for crime instead of trying to make a kitchen knife that can't be used for stabbing someone.

For a kitchen knife this was okay, but the AI firms think that they’ve built a drone that’s the size of a phone but can fly 100km and can hold a kitchen knife. It might be used to assassinate someone before others can react or even catch them.

An ordinary kitchen knife can be used to assassinate someone before others can react. How do you think the time it takes to do that compares to the police response time?

In both cases the catching them comes after the fact and has the purpose of deterring rather than impeding.

Re: Grok 4.6

#446

Post by GenerWork »

leerob wrote: post #93
GenerWork wrote: post #25

>Grok 4.6 produces stronger first passes on visual and interactive projects than we typically saw with Grok 4.5. Given a concrete product idea, it is able to establish structure and visual language for an application in one pass. As a designer, I'm always hesitant to believe these statements until there's independent comparisons between the old & new model, as well as comparisons to human made flows. Design can be so…

(I work on Grok) We've been working on teaching the model how to reason about great visual design principles. Obviously this is hard and somewhat subjective, but through a combination of writing down these principles (e.g. how to think about systems, not just "use this italic serif font on marketing pages"), and then creating a lot of data to pairwise compare designs/outputs, we've made a notable improvement over G4.…

Good to know! If I could make one suggestion, it'd be great to have an example or two in the press release where you have a prompt, and show what the newest model and the prior model made. This would make it super easy to compare the differences between said models.

Re: Grok 4.6

#447

Post by sailfast »

causal wrote: post #23

Anyone else find it weird how within 2 months of Fable releasing all the major labs suddenly had Fable-level models? Trying to think of explanations: 1) AI researchers talk and change companies often, so techniques circulate. This feels implausible because training and shipping a new model ought to take longer than 2 months? 2) Distillation - also implausible for the reason above. 3) Benchmark hacking. AI companies h…

Do they have Fable level models? Or are they all saying “hey we’re dangerous too!” and hoping to get some token spend out of it?

Re: Grok 4.6

#449

Post by whatthesmack »

itsdesmond wrote: post #259
throwaway-blaze wrote: post #193

Earlier quoted context omitted.

Not unless you're here illegally. And it has nothing to do with skin color. Just the basic fact that a country not in control of its borders ceases to be a country.

> Remigration is a far-right concept referring to the ethnic cleansing[1] via mass deportation of non-white minority populations, especially immigrants and sometimes including native-born citizens, to their place of racial ancestry.[2] https://en.wikipedia.org/wiki/Remigration It’s right there at the top. One google search is all it takes. You didn’t even, for a second, think to familiarize yourself with the remigrat…

I reject your (and Wikipedia’s) theory of “remigration” arbitrarily defining something that is (not actually) happening in the US. People are being deported from the US based on their lack of legal presence in the country, which is what every country also does. Nobody is being deported because of their skin color.

Also, nobody is jumping to the conclusion that you’re wrong about something that is not actually happening. It’s just a simple fact that what you’ve stated is preposterous to begin with and is not the policy of any recent law or administration in the US.

Re: Grok 4.6

#450

Post by jannyfer »

AnthonyMouse wrote: post #445
jannyfer wrote: post #436

Earlier quoted context omitted.

For a kitchen knife this was okay, but the AI firms think that they’ve built a drone that’s the size of a phone but can fly 100km and can hold a kitchen knife. It might be used to assassinate someone before others can react or even catch them.

An ordinary kitchen knife can be used to assassinate someone before others can react. How do you think the time it takes to do that compares to the police response time? In both cases the catching them comes after the fact and has the purpose of deterring rather than impeding.

Hm? I'm saying that the AI firms used to have the philosophy of "ok this kitchen knife is dangerous but we'll catch the murderers" on older AI models. But now, the AI firms think that any average person could send a flying knife to attack a political figure they don't like, from the comfort of their home. Now give this to a billion people, and suddenly you have chaos. So to continue the analogy, now they're mandating drone registration, GPS tracking, etc.

And then a Chinese company sells a drone with no registration or tracking and suddenly people want to turn to legislation to ban Chinese drones.

Hey this analogy is working really well

Post reply on HN