Hackworth

DeepMind keeps trying to build a model architecture that can continue to learn after training, first with the Titans paper and most recently with Nested Learning. It’s promising research, but they have yet to scale their “HOPE” model to larger sizes. And with as much incentive as there is to hype this stuff, I’ll believe it when I see it.

Everyone seems to be tracking on the causes of similarity in training sets (and that’s the main reason), so I’ll offer a few other factors. System prompts use similar sections for post-training alignment. Once something has proven useful, some version of it ends up in every model’s system prompt.

Another possibility is that there are features of the semantic space of language itself that act as attractors. They demonstrated and poorly named an ontological attractor state in the Claude model card that is commonly reported in other models.

If the temperature of the model is set low, it is less likely to generate a nonsense response, but it also makes it less likely to come up with an interesting or original name. Models tend to be mid/low temp by default, though there’s some work being done on dynamic temperature.

The tokenization process probably has some effect for cases like naming in particular, since common names like Jennifer are a single token, something like Anderson is 2 tokens, and a more unique name would need to combine more tokens in ways that are probably less likely.

Quantization decreases lexical diversty, and is relatively uniform across models. Though not all models are quantized. Similarities in RLHF implementation probably also have an effect.

And then there’s prompt variety. There may be enough similarity in the way in which a question/prompt is usually worded that the range of responses is restrained. Some models will give more interesting responses if the prompt barely makes sense or is in 31337 5P34K, a common method to get around alignment.

I didn’t say they were. I said A.I. is. The delay makes remote control difficult at long distances. Hence, AutoNav.

I’m super curious about the small text underneath.

I’m embarrassed I skimmed right over that on a first glance. Looks like the original was hematite. I’m going to pretend I was making a bad LotR joke.

Ah, I’d never heard that. Found the image and it appears to have originally been hematite.

I’m confused by the matte out. Is it to anonymize the ring? Something written on it, maybe?

Aliens

Empathize as in understand motivations and perspectives: 8

With some effort to communicate, I can usually understand how someone got where they are. It’s important to me to understand as many ways of being as possible. It’s my job to understand people, but the bigger motivation is that it bugs me if I don’t understand the root of a disagreement. Of course, this doesn’t mean I condone their perspective, believe it’s healthy/logical, or would recommend it wholesale to others.

Just pointing out the definition of A.I. that I am using in this context.

GPTs are based on a deep learning architecture called the transformer. Deep learning is a subset of machine learning, which is itself a subset of artificial intelligence. -Wikipedia

Being Libertarian

A.I. is much more suited to space travel than humans are. The next few decades probably determine whether future aliens first encounter Curiosity’s progeny or MechaHitler grey goo.

I ruminate on this from time to time. I’m not particularly well read on these things, but this is the closest I’ve managed to make sense of it: For whatever reason (and thar be many), the trumpite has embraced denigrating others as an acceptable way to soothe the ego. Unhealthy as it is, this kind of projection/displacement is by no means an uncommon trait in any demographic. Though it seems to be more common in groups that highly value hierarchy (as the Right typically does). On its own, utilizing this as a motivating force yields diminishing returns as shame or just boredom creep in. And so the aspiring demagogue hitches denigration to anger, goads projection with scapegoating, and ultimately harnesses hate to do evil.

But this takes time. Trump didn’t skip all the way to invading cities and tearing down a third of the White House on day one. Trumpites have been lead gradually by these mechanisms and a host of complimentary social tactics to do more and more shameful things. And in doing, their egos are resiliently bridled to Trump’s. To turn against him now would mean facing feelings of abject humiliation and shame/guilt, and in some cases a complete reset of personal identity. Most people aren’t willing to do that until they encounter tragic and very personal consequences. So they persist in delusion, which comes naturally to parts of the religious demographics… but that’s a whole other can of worms.

She’ll Hunt - Banning Books

Macklemore - Fucked Up

Notably, the drummer from KISS, the actor who played Shaft, and Beyonce’s father.

I’ll second Dispatch. Enjoyed it more than I thought I would and legitimately looking forward to the next chapters.

Yeah, there’s no real data for “show signs of manic or psychotic crisis,” as far as I can tell. I just went for the low-hanging fruit, since mania is often part of bipolar (manic-depressive). But if just bipolar is sitting at 2.8% of Americans in a given year, I think it’s reasonable to say the loosely defined global stats in the article aren’t notably high.

An estimated 2.8% of U.S. adults had bipolar disorder in the past year. -NIH