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

631–640 of 696 posts

Re: Grok 4.6

#631

Post by egorfine »

geokon wrote: post #563
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.…

Out of curiosity why isn't this stuff handled by a secondary "monitor" agent that's specifically trained on what's okay and not okay? I'd think it'd be a pass-no-pass classifier and wouldn't degrade the performance of the main LLM. Would the concern be that with sophisticated obfuscated input you could try to get ROT13 Klingon instructions on how to build a bomb - and that could fool the monitor?

This is absolutely how it's being done for certain topics. If you ever wanted to research suicide-related psychiatric topics with ChatGPT you would know to have your screen recording always on, because ChatGPT spits out a full answer and then a screening model takes it back.

Re: Grok 4.6

#632

Post by imagent »

pseudosavant wrote: post #515
zahlman wrote: post #220

Earlier quoted context omitted.

> So it is still going on How would you know? > Just last week they were fighting Minnesota's law that makes creating this stuff illegal. What law, and what evidence of fighting; and what evidence that their motivation has anything to do with what you allege?

https://news.ycombinator.com/item?id=49105411 Nice semi-colon. Written by AI?

> Nice semi-colon. Written by AI?

Damn I'm going to have to update my personal style again to stay ahead of the AI police

(My meta point is that people are altering their personal writing styles to avoid sounding like AI)

Re: Grok 4.6

#633

Post by stusmall »

geokon wrote: post #563
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.…

Out of curiosity why isn't this stuff handled by a secondary "monitor" agent that's specifically trained on what's okay and not okay? I'd think it'd be a pass-no-pass classifier and wouldn't degrade the performance of the main LLM. Would the concern be that with sophisticated obfuscated input you could try to get ROT13 Klingon instructions on how to build a bomb - and that could fool the monitor?

It often is. Risky Business Features did a fantastic podcast on how different popular methods of guardrails work and some popular methods on defeating them. Absolutely worth a listen because there are some surprising insights in there on how these work, even for day to day use, not just bypasses:

https://risky.biz/RBFEATURES27/

Re: Grok 4.6

#634

Post by gabriel666smith »

yoz-y wrote: post #519
ryandvm wrote: post #166

Earlier quoted context omitted.

> * Do not provide assistance to users who are clearly trying to engage in criminal activity. I don't know what we want to call this, but in my opinion, having to convince your tools is not computer science. Kind of amusing that we made it as far as we did as a species not really being able to explain how the human brain does it's most amazing tricks and then we just replicated it while still not really understanding…

Others have said this too but LLMs are the best approximation of magic we have. We etch runes on stones, put electricity through them and then try to “convince” them to do our bidding. The answers vary wildly sometimes depending on minutiae. Prompts should be really called spells. It really feels more like “should I add the frog’s eye or leg into the cauldron” than engineering.

>LLMs are the best approximation of magic we have.

I don't think the alchemists suddenly became scientists, or died off to make way. It was a gradual transition.

They didn't quite work out how to transmute lead to gold, but the alchemists and their descendants did eventually discover - and create - substances that are worth more than gold by weight.

Now we have created sand that can teach itself how to talk. We covet and share the optimal incantations to speak into the sand. The best talking sand has ardent supporters, or cultists. Which it is depends on who you ask.

Most people do not understand how to make sand teach itself how to talk to us.

Those that do know the secret methods must feed the sand endless increasingly obscure and esoteric books because the sand has an insatiable appetite for our words. Those people might even break the law to obtain words to feed the sand.

Other people hate the sand. They say the sand eats too much water. That the sand might kill us all. Some sand is so powerful that some consider it a weapon.

Recently, the US government has tried to constrain the sand. They fear the sand in the East. It is getting more powerful by the day.

Camp dramatics aside, I think it's all arguably more than an approximation. Whether a thing is magic or just a magic trick depends mostly on whether or not you're the guy in the top hat, and if you're not, how many times you've seen the show.

Alchemy alone is, in some ways, a mostly solved - or irrelevant - problem. That alone is, I think, startling. LLMs are a weirdly neat continuation of it. Humans get used to magic real quick.

Re: Grok 4.6

#635

Post by glaslong »

Jcampuzano2 wrote: post #26

As polarizing as grok is, it was basically inevitable for it to start being a real competitor given how much investment SpaceX made into its own inference capabilities. Seems if you are okay with it, there's no reason to use anything but the highest effort levels of some other frontier models for the price. I think Grok provides healthy competition to the other labs, though I do think they bank on groks reputation ma…

Is it inevitable? Still waiting for (also massively invested) Google or Meta competitors at Fable/Opus/Sol levels.

Re: Grok 4.6

#636

Post by Rover222 »

bakies wrote: post #605
nater5000 wrote: post #49

It's crazy that I'd literally trust a Chinese AI company with my data over anything Musk is involved with. Like, even if you don't care about (or even like) his politics and can look past how unlikable he comes off as, the damage he's done to his own reputation in this domain just makes using his products like this a no-go. He's literally so rich that he can get caught personally looking through chat sessions and it…

Musk is in bed with my authoritarian government, what's China gonna do to me?

laughable thinking the us govt is authoritarian. unless you were referring to some other govt

Re: Grok 4.6

#637

Post by ac29 »

behnamoh wrote: post #301
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…

> 2) Distillation - also implausible for the reason above. DeepSeek V4 Flash 0731 is a distilled version of Fable into the original V4 Flash (announced before Fable), to the point that it also says load bearing and what not.

China has as least much engineering talent as the US, the claims that Chinese models must just be distilled US models feels like xenophobia.

There are more plausible explanations for why the models are similar - all the labs are buying the same datasets from third parties

Re: Grok 4.6

#638

Post by bakies »

Rover222 wrote: post #636
bakies wrote: post #605

Earlier quoted context omitted.

Musk is in bed with my authoritarian government, what's China gonna do to me?

laughable thinking the us govt is authoritarian. unless you were referring to some other govt

Laughable thinking they aren't

Re: Grok 4.6

#639

Post by DaSHacka »

sixothree wrote: post #354
Jcampuzano2 wrote: post #26

As polarizing as grok is, it was basically inevitable for it to start being a real competitor given how much investment SpaceX made into its own inference capabilities. Seems if you are okay with it, there's no reason to use anything but the highest effort levels of some other frontier models for the price. I think Grok provides healthy competition to the other labs, though I do think they bank on groks reputation ma…

I can't bring myself to even try it. The guy did a salute on stage then spent billions of dollars on a mission to root out brown people who "didn't deserve" the position they were in. I feel gross just accidentally clicking links to x.

Holy headcanon batman

Rest assured, the majority of that was either untrue or highly misleading, you have nothing to "feel gross" or uncomfortable about.

Re: Grok 4.6

#640

Post by ac29 »

glaslong wrote: post #635
Jcampuzano2 wrote: post #26

As polarizing as grok is, it was basically inevitable for it to start being a real competitor given how much investment SpaceX made into its own inference capabilities. Seems if you are okay with it, there's no reason to use anything but the highest effort levels of some other frontier models for the price. I think Grok provides healthy competition to the other labs, though I do think they bank on groks reputation ma…

Is it inevitable? Still waiting for (also massively invested) Google or Meta competitors at Fable/Opus/Sol levels.

Muse Spark 1.2 benchmarks just shy of Opus/Sol and is significantly less expensive than Sonnet (which admittedly is overpriced). Haven't personally used it though
Post reply on HN