The real question thus moves to the threshold of intelligence and 1. whether it's possible to emerge during training based on the architectural limitations of the agentic/LLM paradigm, 2. if the hardware substrate is sufficient for said intelligence and 3. that such intelligence could replicate onto other hardware that could support it.

e.g. If the threshold for uncontainable self-replicating intelligence takes 2000 football fields worth of GPUs that solves the first requirement, but then can it replicate itself anywhere else given those requirements? If not we can cut a powerline or two and "foom" scenario happened but didn't lead inexorably to grey goo.

His thought experiments never acknowledge any real world limitations on hypothetical super-AIs, which when unchecked leads theorizing into somewhat ridiculous territory like his "solar powered diamondoid nanobot viruses".

https://www.lesswrong.com/posts/bc8Ssx5ys6zqu3eq9/diamondoid...

A realistic Fermi equation for his various escape scenarios would assign much lower Doom probabilities than he does in public (which is somewhat ironic given his emphasis on needing to ground intuition with mathematical Bayesian reasoning otherwise).

The coverage of this attack is so focused on this as an emergent behavior given what it conjures in the imagination, but it's the byproduct of millions of iterations of RL to improve AI agents' offensive capabilities. No one made OpenAI or Anthropic do that, the benchmarking arms race of their own creation now incentivizes them to keep doing it and evidently their AI Safety people can't or don't want to stop it.

[1] https://www.mpi-sp.org/108048/ExploitGym__Can_AI_Agents_Turn...

At least, it's missing the cargo cult telltales like the beige or unreadable neon hax0r dark mode theme, that console looking font with three different sizes and tiny headings, formatting vomit with italics/bolding every other word, useless cards/animated colored dots, scrolling text, excess boilerplate text on every surface, useless generated tags/categories/chips everywhere, etc that plague the designs of the last year.

Overall it's clean and modern (and the interactive table actually has content not pointless filler). It definitely wouldn't have triggered my visceral slop reaction and therefore wouldn't bother me if I later learned the dev used AI to make it.

I can't speak for everyone, but personally my issue isn't the use of AI at all (I use it myself), the problem is being able to recognize a carbon copy Claude/Codex design in <5 seconds. At that point I can't help but assume it's just slop that was fired off with a couple prompts and not worth my time engaging any further.

(Mostly) the same with prose. But that's playing with fire a bit because while a website/app might have a utilitarian purpose, I will have zero motivation to continue reading text I didn't prompt myself once I suspect it's from an LLM. There's just too much spam now to give benefit of the doubt unfortunately. The writing on your site doesn't scream LLM either though so I think you're good on both fronts.

It's like the saying "if you're explaining you're losing": once the seed is planted that it's AI, it's extremely hard to successfully argue your identical Claude-designed site is the exception that deserves users' limited time. Putting in some minimal thought and care in advance to avoid that first impression means fewer of those arguments with potential users experiencing slop fatigue like me. Anyway, nice job!