It's provided the current time together with other 20k sys-prompt tokens, so substantially more diluted influence on the behaviours..?

Folks like this guy hit it on hyperspeed - 

https://www.facebook.com/reel/1130046385837121/?mibextid=rS40aB7S9Ucbxw6v

I still remember university teacher explaining how early TV transmission were very often including/displaying ghosts of dead people, especially dead relatives.

As the tech matures from art these phenomena or hallucinations evaporate.

 you seem to report one OOM less than this picture in https://alexiglad.github.io/blog/2025/ebt/#:~:text=a%20log%20function).-,Figure%208,-%3A%20Scaling%20for

Link to Induction section on https://www.lesswrong.com/lw/dhg/an_intuitive_explanation_of_solomonoff_induction/#induction seems broken on mobile Chrome, @habryka 

I've heard that hypothesis in a review of that blog post of Anthropic, likely by 

AI Explained

maybe by

bycloud

.

They've called it "Chekov's gun".

What's your view on sceptic claims about RL on transformer LMs like https://arxiv.org/abs/2504.13837v2 or one that CoT instruction yields better results than <thinking> training?

Not the content I expect labeled AIb Capabilities,

although I see how that'd be vindicated. 

By the way, if I write an article about LMs generating SVG, that's a plaintext and if I put an SVG illustration up, that's an image, not a plaintext?

Trivial, but do token-based LMs follow instructions like "only output tokens '1', '2', '3'" where they'd output 123 as one token without that instruction?

I'd update my take from a very pessimist/gloom one to an (additional) excited one: Those more intelligent models building a clear view of the person they/it interacts with is a sign of emerging empathy, which is a hopeful property for alignment/respect.

False Trichotomy?

Your model assumes that one cannot be all three, however, some roles demand it, and in reality people do navigate all three traits, my top example would be empathic project managers.