[flagged]
[flagged]
Grok 4.6
471–480 of 696 posts
Re: Grok 4.6
#472Earlier quoted context omitted.
There is a widespread belief that the nature of intelligence is scalar, like how a person can have 100x more wealth than another person. If this were true, then we’d probably see breakaway RSI from a single lab. But I think we’re discovering that intelligence is about universality, not magnitude. This is analogous to how building a universal Turing machine wasn’t merely a matter of building a calculator that could mu…
But in theory you can make an LLM A LOT faster than a human. You can also run massive amount of LLMs in parallel. There might be a limit to a normal LLM but not to theo everall system.
> There might be a limit to a normal LLM but not to theo everall system.
Bigger limit and no limit are very different.
Re: Grok 4.6
#473Earlier quoted context omitted.
The alternative is Claude-style "safeguards" aka censorship, which: 1. doesn't eliminate the possibility of a jailbreak anyway 2. frequently has false positives, triggering on innocuous requests, which is just really annoying Not saying that we can't (or shouldn't) do better than Grok, but I really don't know what the best solution is here...
> 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.
If that could be done before any damage sure but preventing a stabbing is better than arresting someone.
Re: Grok 4.6
#474Earlier quoted context omitted.
Source for this? This seems like a crazy leak if it's their real system prompt. I find it hard to believe since I have tried system prompts like this and it doesn't work that well, just pollutes the user's context. A great test for any LLM is to ask its name - Mistral will respond with all kinds of stuff, sometimes other models' names, revealing that it has trained on other models. Grok doesn't though. It is "witty a…
Crazy? System prompt leaks are old news with dozens of trix to do it
In your mind do you think the user request goes straight to the LLM???
I hope that's not what people are doing
I only figure [older pulls of Mistral 7b] were doing it, since it was so easy to exfiltrate false names, so I don't mean it's totally unheard of, but in 2026 I hope people are treating the LLM as untrustworthy - like the client in client/server setups.
Re: Grok 4.6
#475Earlier quoted context omitted.
Crazy? System prompt leaks are old news with dozens of trix to do it
In your mind do you think the user request goes straight to the LLM??? I hope that's not what people are doing I only figure [older pulls of Mistral 7b] were doing it, since it was so easy to exfiltrate false names, so I don't mean it's totally unheard of, but in 2026 I hope people are treating the LLM as untrustworthy - like the client in client/server setups.
In naive implementations like Grok that is exactly what happens.
Re: Grok 4.6
#476Earlier quoted context omitted.
In your mind do you think the user request goes straight to the LLM??? I hope that's not what people are doing I only figure [older pulls of Mistral 7b] were doing it, since it was so easy to exfiltrate false names, so I don't mean it's totally unheard of, but in 2026 I hope people are treating the LLM as untrustworthy - like the client in client/server setups.
In naive implementations like Grok that is exactly what happens.
Does Grok not have native models? What are you saying precisely
Re: Grok 4.6
#477Earlier quoted context omitted.
[flagged]
That has been the case for a while now: https://en.wikipedia.org/wiki/Ashcroft_v._Free_Speech_Coalit...
I think the comment you replied to was referring to the fact that when Twitter was taken over the entire Trust and Safety team was done away with. This has allowed child sexual abuse material to flourish on the platform.
Re: Grok 4.6
#478Grok used to be useful for a while for free... now it answers one question then demands I buy GrokPlus. Meh
Re: Grok 4.6
#479Earlier quoted context omitted.
These system prompts are not the only safety layer that these models use. There's other more deterministic filters in place both on input and (streaming) output.
Is there concrete evidece that those are xAI's default prompts anyway? They seem plausible enough but how would company outsiders know?
you can just look at the traffic in mitmproxy.
Re: Grok 4.6
#480Earlier quoted context omitted.
Source for this? This seems like a crazy leak if it's their real system prompt. I find it hard to believe since I have tried system prompts like this and it doesn't work that well, just pollutes the user's context. A great test for any LLM is to ask its name - Mistral will respond with all kinds of stuff, sometimes other models' names, revealing that it has trained on other models. Grok doesn't though. It is "witty a…
Crazy? System prompt leaks are old news with dozens of trix to do it
mitmproxy