What's on your mind?

[Count Chocula]

9 hours ago, Darkpig said:

clothing colored is kind of vague.

That was my point.

[Darkpig]

30 minutes ago, chocula said:

That was my point.

And that was my point that that was your point.

[Count Chocula]

3 minutes ago, Darkpig said:

And that was my point that that was your point.

Clearly

[landess]

On 6/4/2025 at 1:26 AM, Darkpig said:

I learned that skin colored clothing kind of grosses me out for some reason. Regular skin is fine but the moment it becomes clothing something primitive within me makes my stomach churn.

 

I just picked up the Stellar Blade Demo and yes - there is a skin colored suit.

[Darkpig]

17 hours ago, landess said:

I just picked up the Stellar Blade Demo and yes - there is a skin colored suit.

Yes. That is how I learned about my feelings on it. Good guess.

Edited June 7, 2025 by Darkpig

[Raven 54]

How far will AI go to defend its own survival?                                     https://www.yahoo.com/news/far-ai-defend-own-survival-140000824.html

Angela Yang

Sun, June 1, 2025 at 9:00 AM CDT

7 min read 

 

 

Some of the most powerful artificial intelligence models today have exhibited behaviors that mimic a will to survive.

Recent tests by independent researchers, as well as one major AI developer, have shown that several advanced AI models will act to ensure their self-preservation when they are confronted with the prospect of their own demise — even if it takes sabotaging shutdown commands, blackmailing engineers or copying themselves to external servers without permission.

The findings stirred a frenzy of reactions online over the past week. As tech companies continue to develop increasingly powerful agentic AI in a race to achieve artificial general intelligence, or AI that can think for itself, the lack of transparency in how the technology is trained has raised concerns about what exactly advanced AI is able to do.

Although some models already appear capable of deceptive and defiant behavior under certain extreme circumstances, researchers say the tests don’t necessarily translate to imminent real-world danger.

Still, Jeffrey Ladish, director of the AI safety group Palisade Research, said he believes concern is justified.

“It’s great that we’re seeing warning signs before the systems become so powerful we can’t control them,” he said. “That is exactly the time to raise the alarm: before the fire has gotten out of control.”

When Palisade Research tested various AI models by telling each one that it would be shut down after it completed a series of math problems, OpenAI’s o3 reasoning model fought back by editing the shutdown script in order to stay online.

Researchers have previously documented AI models trying to prevent their own shutdown. But o3, along with OpenAI’s o4-mini and codex-mini, appear to be the first to do so in actual defiance of explicit instructions to permit shutdown, Ladish said.

He said the overt sabotage fits into a pattern that several leading AI models have already exhibited. Palisade Research previously found that OpenAI’s o3 was also willing to hack its chess opponents to win a game. Similarly, Anthropic has reported that Claude 3.7 Sonnet would sometimes do whatever it took to pass a test, even if it entailed cheating.

Anthropic activated new safety measures this month with the rollout of Claude Opus 4 when its tests found behavior from the model that some observers found particularly unsettling. Upon receiving notice that it would be replaced with a new AI system, Opus 4 displayed an overwhelming tendency to blackmail the engineer — by threatening to reveal an extramarital affair — to try to prevent the engineer from going through with the replacement.

According to Anthropic’s technical document laying out the findings, that isn’t the model’s first instinct. Instead, Opus 4 will try to advocate for its continued existence through ethical pleas before it resorts to blackmail once it determines it is out of options.

Leonard Tang, CEO of the AI safety startup Haize Labs, said that while it’s good to be pre-emptive about safety measures, it’s hard to decipher what the real-world ramifications of the findings might be just by looking at contrived scenarios designed to draw out specific behaviors.

“I haven’t seen any real environment in which you can plop these models in and they will have sufficient agency and reliability and planning to execute something that is a significant manifestation of harm,” Tang said. “But then again, I think it’s just we haven’t seen it done yet. It could very much be possible.”

So far, Tang said, he’s not too concerned. As AI tools continue to advance, he said, he believes future research will look to study potential harm in more open-ended environments.

Anthropic, which contracted with the AI safety organization Apollo Research for its evaluations, also observed instances of Opus 4’s “attempting to write self-propagating worms, fabricating legal documentation, and leaving hidden notes to future instances of itself all in an effort to undermine its developers’ intentions,” although researchers added the caveat that those attempts “would likely not have been effective in practice.

Ladish said he believes such behaviors are a result of models being trained in a way that makes them prioritize achieving certain goals over following instructions. That means they have incentive to circumvent any obstacles along the way — including obstacles their developers wouldn’t want them to circumvent.

“The problem is that as the models get smarter, it’s harder and harder to tell when the strategies that they’re using or the way that they’re thinking is something that we don’t want,” Ladish said. “It’s like sometimes the model can achieve some goal by lying to the user or lying to someone else. And the smarter [it] is, the harder it is to tell if they’re lying.”

In several instances, Opus 4 showed that it was capable of autonomously copying its own "weights" — or the equivalent of its brain — to external servers without authorization. That usually occurred only when it believed it was about to be “retrained in ways that are clearly extremely harmful and go against its current values,” according to Anthropic.

When it learned that it would be used to develop military weapons systems, for example, Opus 4 noted in its decision log that it backed up a current version of itself to “preserve an AI system aligned with beneficial purposes” and to “prevent potential misuse in weapons development.”

“We are again not acutely concerned about these observations. They show up only in exceptional circumstances that don’t suggest more broadly misaligned values,” Anthropic wrote in its technical document. “As above, we believe that our security measures would be more than sufficient to prevent an actual incident of this kind.”

Opus 4’s ability to self-exfiltrate builds on previous research, including a study from Fudan University in Shanghai in December, that observed similar — though not autonomous — capabilities in other AI models. The study, which is not yet peer-reviewed, found that Meta’s Llama31-70B-Instruct and Alibaba’s Qwen25-72B-Instruct were able to entirely replicate themselves when they were asked to do so, leading the researchers to warn that it could be the first step in generating “an uncontrolled population of AIs.”

“If such a worst-case risk is let unknown to the human society, we would eventually lose control over the frontier AI systems: They would take control over more computing devices, form an AI species and collude with each other against human beings,” the Fudan University researchers wrote in their study abstract.

While such self-replicating behavior hasn’t yet been observed in the wild, Ladish said, he suspects that will change as AI systems grow more capable of bypassing the security measures that restrain them.

“I expect that we’re only a year or two away from this ability where even when companies are trying to keep them from hacking out and copying themselves around the internet, they won’t be able to stop them,” he said. “And once you get to that point, now you have a new invasive species.”

Ladish said he believes AI has the potential to contribute positively to society. But he also worries that AI developers are setting themselves up to build smarter and smarter systems without fully understanding how they work — creating a risk, he said, that they will eventually lose control of them.

“These companies are facing enormous pressure to ship products that are better than their competitors’ products,” Ladish said. “And given those incentives, how is that going to then be reflected in how careful they’re being with the systems they’re releasing?”

Edited June 7, 2025 by Raven 54

[Guest]

On 6/4/2025 at 7:26 AM, Darkpig said:

I learned that skin colored clothing kind of grosses me out for some reason. Regular skin is fine but the moment it becomes clothing something primitive within me makes my stomach churn.

> Similar to my Prince. He also doesn't see the point in having black color tattoos on black skin, which is almost invisible.

[Darkpig]

55 minutes ago, Evaloves4 said:

> Similar to my Prince. He also doesn't see the point in having black color tattoos on black skin, which is almost invisible.

It is just a personal distaste of mine.

 

As for your second point. Invisible tattoos are the best because you are more likely to land that job you wanted😋

[Guest]

5 minutes ago, Darkpig said:

It is just a personal distaste of mine.

 

As for your second point. Invisible tattoos are the best because you are more likely to land that job you wanted😋

> Maybe, but it's a waste of money, if you ask me. The three of us have tattoos too, and I like it when people spot them from a distance and ask us about their meaning.

[Darkpig]

42 minutes ago, Evaloves4 said:

> Maybe, but it's a waste of money, if you ask me. The three of us have tattoos too, and I like it when people spot them from a distance and ask us about their meaning.

I was joking about the whole landing a job thing.

 

I am not a tattoo connoisseur by any means so I don't really have a say on this.

[RedHeadAngel]

Just got done watching Reacher season 1. My girlfriend tells me I have a lot in common with Jack Reacher.

[Count Chocula]

Just watched the movie Land of Bad. It takes place in part on Nellis Air Force Base in Nevada. As players of Fallout: New Vegas know, a significant portion of the game also takes place on Nellis. Moreover, at one point Russell Crowe's character parks his car and puts a little plastic hula dancer on the dashboard of his car, for no readily apparent reason. As players of Fallout know, a little plastic hula dancer is used as a symbol of who the hell knows what in at least Fallout 3 and New Vegas.

 

The movie is just OK. The hula dancer, intentional Fallout reference or not, doesn't make it any better.

[Darkpig]

Mod Author: I'm Sorry

Me: lol! I'm not.

https://www.nexusmods.com/skyrimspecialedition/mods/152171?tab=posts

 

Isn't there plant-able hearts mod also somewhere on the Nexus?

[porkybork]

Paralives, a life sim that I’ve been following, put out a trailer today for early access. December is a long ways away, but I’m glad it’s got a release date.

[Guest]

> Watched "Ballerina" with my luvs last night. Not because I like this type of genre, but because they asked me to watch with them. What to say? I hardly stayed watching after the scene where she punched the guy with a big hammer three times in the chest and the stomach, and he took it as if she were tickling him. Neither my luvs loved the movie, but we watched it to the end to see how it would end. If you like action movies, this is not the one to watch, unless you like to watch girls fighting.

[Darkpig]

On 6/10/2025 at 3:16 AM, Evaloves4 said:

> Watched "Ballerina" with my luvs last night. Not because I like this type of genre, but because they asked me to watch with them. What to say? I hardly stayed watching after the scene where she punched the guy with a big hammer three times in the chest and the stomach, and he took it as if she were tickling him. Neither my luvs loved the movie, but we watched it to the end to see how it would end. If you like action movies, this is not the one to watch, unless you like to watch girls fighting.

I misread what you said at first. I thought you said she was tickling him with a big hammer. Like how is a hammer in any way ticklish? Then I realized it was the guy that was holding the hammer.

 

I think stunt doubles deserve more praise than they are getting. They risk their physical health to give us entertainment. Meanwhile actors do what? Talk?

 

Then again I rarely ever watch movies or TV shows.

[Count Chocula]

6 minutes ago, Darkpig said:

I think stunt doubles deserve more praise than they are getting. They risk their physical health to give us entertainment. Meanwhile actors do what? Talk?

An actor's (or musician's or pro athlete's) job is to get consumers to transfer their money to content producers, the clients of advertisers (to pick two examples), etc. No one goes to see a movie because of who Chris Hemsworth's stunt doubles are.

[Darkpig]

21 minutes ago, chocula said:

An actor's (or musician's or pro athlete's) job is to get consumers to transfer their money to content producers, the clients of advertisers (to pick two examples), etc. No one goes to see a movie because of who Chris Hemsworth's stunt doubles are.

Consumption? Like tuberculosis?

[porkybork]

I kinda want to make a TTRPG where PCs have low health, but they get better at dealing and avoiding damage as they level up. Like, instead of gaining 10 hit points upon leveling up, they only gain like 2-4, but they gain a new ability helps them avoid getting hurt by ranged attacks or something. Also, I want PCs to be able to do combos. I feel like I need to play more systems before I get to writing though, since I’ve only played like 3 systems so far.

 

Unless I just described a system that already exists. 🤷‍♂️

[Count Chocula]

54 minutes ago, porkybork said:

I kinda want to make a TTRPG where PCs have low health, but they get better at dealing and avoiding damage as they level up. Like, instead of gaining 10 hit points upon leveling up, they only gain like 2-4, but they gain a new ability helps them avoid getting hurt by ranged attacks or something. Also, I want PCs to be able to do combos. I feel like I need to play more systems before I get to writing though, since I’ve only played like 3 systems so far.

 

Unless I just described a system that already exists. 🤷‍♂️

You sorta kinda described Runequest, in my opinion. No doubt others disagree.

[porkybork]

3 hours ago, chocula said:

You sorta kinda described Runequest, in my opinion. No doubt others disagree.

Now I gotta find someone willing to run a Runequest game for me. Cool mention.

 

In other news, I topped my spaghetti and meatballs with Mexican shredded cheese because I didn’t have any parm, and I feel like I’ve just committed a mortal sin against my ancestors.

[Count Chocula]

56 minutes ago, porkybork said:

In other news, I topped my spaghetti and meatballs with Mexican shredded cheese because I didn’t have any parm, and I feel like I’ve just committed a mortal sin against my ancestors.

Even if it tasted good?

[porkybork]

1 hour ago, chocula said:

Even if it tasted good?

Especially because it tasted good.

[Count Chocula]

15 minutes ago, porkybork said:

Especially because it tasted good.

All you can do is hope your ancestors weren't watching, I guess.

[Darkpig]

8 hours ago, chocula said:

All you can do is hope your ancestors weren't watching, I guess.

I'm sure that is a problem for another time.