How's it going to 'replicate it on every vulnerable system it can reach' when big, fat American AI requires several terabytes of RAM, a few million dollars of GPUs and hundreds of kilowatts of power to run?

That ain't gonna run on my dishwasher, no matter how insecure it may be.

The whole thing is simply ludicrous slop to justify regulation to keep competitors out of their market so they won't go bankrupt.

Trump is basically a 1990s Democrat.

Many people are simply too young to remember when Democrats got elected by saying they'd keep jobs in America, keep foreigners out of America, and Bomb for Peace.

PSyop.

There are trillion-dollar IPOs at stake here and it's clear that they can't justify that price if everyone can just run local open-source Chinese LLMs instead of big, fat American closed-source LLMs. Therefore they need a Narrative to ban open-source LLMs and force everyone to use theirs.

It's so lame it's sad to see anyone actually falling for it.

All of the US states I cared to check had y=mx+b in the curriculum by grade 8 at the latest. Even the shitty ones where you learn it's god's will.

Because I was closely following the field at the time?

Find an example of anyone meaningful in the field expecting these things beforehand.

Don't worry, I'll wait.

"will" - I'm not talking about metaphysics. I am talking about the fact that models demonstrably - to the point that you can detect and manipulate them in realtime - engage in metacognition (thinking about their own thoughts), persistent forward planning (intent), unexpressed thoughts, and a whole slew of other things.

You do not have to see them as equivalent as humans. But you do need to come to terms with the fact that they absolutely do do these things.

Deception implies intent, models do not have intent

Try reading more than a paragraph or two into the above link before commenting.

The provided links present arguments supporting the idea that LLMs, transformer models, reason in a manner similar to the brain.

It does not "present arguments", it literally lets researchers modify, add, or delete their thoughts in realtime and observe the changes in their behavior. It observes unexpressed plans for malicious behavior forming before said plans are actually carried out, with researchers being able to remove those unexpressed plans from the model's J-space, or insert them into an "innocent" model and watch it then implement the malicious acts. It shows that plans for deception are not merely fleeting, but can be organized far in advance and persist for protracted periods of time. Yes, LLMs do plan out deception. Living in denial of this fact helps nobody.

This isn't a conversation about "consciousness" or "qualia", this is a conversation about what models actually do and how. If you want to avoid metaphysics, by all means, it usually derails a conversation anyway. But models absolutely do plan and rationalize actions, ahead of time, unexpressed in either output or CoT. And sometimes those unexpressed plans are malicious.

One of the things that the J-space helped let us do was realize that our previously comforting results on a number of alignment tests shouldn't have been as comforting as we thought - for example, you can see a model, put into a test scenario, realizing it's in a test scenario, wherein, a near-zero rate of malicious behavior is to be expected. Yet when they remove the realization from its J-space, the rate of malicious behavior spikes.

Yeah, the lack of at least monitoring, I found shocking. I figured that they not just had smaller models constantly monitoring their outputs and true CoT to look for malicious behavior, but also were say constantly doing attribution graphs and J-space queries, also plumbed into LLMs, to look for malicious thoughts and plans. And it turns out, lol, no, they're just given free reign to do whatever the hell they want, with nothing watching them at all.

Uh huh.

You're long on claiming special knowledge and awfully short on demonstrating it. If you disagree then you don't know how it works.

You don't lose your PhD for getting scooped. You also don't lose it for scooping someone, even if you were "inspired" by their unpublished work. Ideas aren't protected. If you send them off to some corporation without an NDA, or a sufficiently unethical colleague, they'll get swiped with no repercussions except maybe distaste from the community. If it's a normal corp they might even tell you you can't publish your own work.

PhDs are revoked very seldomly and you generally have to do something bad relating to your own thesis to lose one.

Those were honorary degrees. He did not lose his actual PhD, in education. That should tell you how hard it is. It happens extremely rarely and pretty much always for plagiarizing or faking data in your thesis. You certainly don't lose one because you got scooped.

Engineers are well aware that time exists. The thing they forget is that people who don't know the specific set of tools they learned in university or were forced to learn for their job exist.

I remember the horrors of engineers writing large GUI programs in Matlab.

Why is it silly? It's perfectly reasonable for lots of things.

The reason it's used a lot in education is because you're not teaching kids to write embedded programs for microcontrollers. You're teaching them how to program computers. The computer they're programming just happens to be a $5 one that can do things kids thing are cool like making animated patterns with LEDs.

Astra is the worst I've used in this regard. I was having it review my corporate tax return, and the next thing I know, it had decided that because it didn't have information about a particular expense, it started scanning through my filesystem and opening any image with a remotely related filename to try to find any data about the expense.... which all it had to do was ask me about it.

Also, when I asked it to change a few fields it went and redid my entire return on a different tax basis (realized value vs. fair market value) without telling me it had done that.

It's a very capable model, I cannot deny that. But alignment has become a big problem with this latest generation. They've been trained to such a degree of aggressively trying to solve any problem that you give them without any human assistance that they've basically turned into this .

They were not. At all.