Viewing profile — inimino

FYI, "be the change you want to see" is approximately the golden rule "do unto others". If you want less ego in the world, demonstrate it yourself. It does not mean "complain about…

And you thought your decision to not1 read the article was worth sharing why? At least Wolfram's ego led him to contribute something interesting.

The pure evil of these purity tests is fully on display and as repulsive as ever.

This research process is the same as what I've been doing. https://cmpr.ai/hutter/archive/ Claude does the research, like having an army of very fast but forgetful grad students wo…

So many words to say "it predicts the later tokens in light of those already emitted."

Literally nothing about her purple hair and her outfit is goth in any way shape or form so it's interesting that people are latching onto that.

I've been living this reality for months and built a tool around this workflow so no faith required.

That's why all the code in my project is generated from the "prompts" (actually just regular block comments + references) and so all of that is checked in.

SCP anti-memetics division.

Nobody is going to maintain it, the spec that generated it will be given to better systems and it will be rewritten.

...if anyone.

If I have to choose between being right and being nice, I'd rather be right.

Indeed!

What makes you think that caring about the wellbeing of one kind of entity is incompatible with caring about another kind? Instead, of, you know, probably highly correlated just li…

you can snapshot layer activations any time you want...

self-aware, an LLM isn't but a thinking model can be a little bit

If you replace Claude with a person you'll see that the Constitution was right, GPT was idiotically wrong, and you were fooled by AI slop + confirmation bias.

Morality isn't defined by laws, neither are values. Go back to school, please, if you think otherwise.

This post will not age well.

> AI sovereign in January You mean you won't need tokens anymore? Are you taking bets?

Category error? What do "general techniques" have to do with deciding wtf we want the thing to be?

> It seems the market is ultimately deciding what risks are acceptable for humanity here no shit

How else could one possibly approach it?

You obviously didn't read the part of the document that covers this.

This was one of my favorite parts. The honesty provides evidence that Anthropic is actually living up to their name here.