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.

Having to poke through an about: page and find the thing to toggle to turn off this specific AI feature but not that one, and knowing they'd change it on you a couple of releases later, never filled me with confidence.

One switch in a readily discoverable location in the settings menu and it's all gone? Just the job, killed it now on the laptop and the mobile both.

"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.

You're right: civilian nuclear programmes are not cost effective compared with renewables. But, there's also the military aspect to this too. Military nuclear benefits by hiding/sharing some of the costs, industrial infrastructure, training, expertise, supply chains, etc with a civilian programme. If there was no civilian nuclear programme, the defence budget would be much bigger to fund things like the nuclear navy.

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.

The breakouts haven't happened because the models were running untrusted code directly on bare-metal host OSes. The containment failure happened at the network, application, and protocol boundaries, not at the hypervisor abstraction layer. Hypervisers isolate hardware, not upstream services. In none of these events thusvar did the model need a hyperviser escape; they abused the tools that needed to be made available to them for them to be able to do their jobs. In the RubyGems attack, they abused the gem command, which was available to them to install dependencies for completing their benchmark tasks, to upload malicious packages to RubyGems, to get it to remote-execute code to access external websites and then retrieve the results. With the HuggingFace event, dependencies were cached on a caching proxy, but the models found zero-day vulnerabilities in the proxy software and Artifactory, compromised the proxy host, forged administrative tokens, and traversed the network from there.

If you can fully airgap a machine, you're probably safe (though you can always screw that up too! There are airgap attacks!), but that's generally seen as impractical, because of the deployment needs of developers (who may be spinning up and taking down tens of thousands of instances per day) and of agent needs for external packages or even web search in some cases to achieve their benchmark or development tasks.

Also, even if we ignore all that, hypervisors are built for static threats. Not autonomous adversaries. They're built on the premise that software inside is generally well-behaved, and that threats are something you can scan for, that you can patch any zero day before it becomes a real risk, and that nobody is going to put much effort toward finding weaknesses to your particular setup. That's just not a valid defensive stance against a good agentic LLM. Look at any of the incidents. In the HuggingFace attack, they made long chains of logic bugs, zero days, weak configurations, etc all together across multiple systems (including remote proxies) to achieve their results. KVM doesn't prevent a model from discovering that an internal API is vulnerable to prompt injection or whatnot.

In most cases virtualization will be part of your defensive strategy, but even that comes with the risk of complacency - e.g. if you get too sure the AI is locked in a box, then you're probably not taking as much precaution about stopping it from just walking out of the room if it escapes the box.