221–230 of 277 posts
Earlier quoted context omitted.
We don’t know how Claude code is internally implemented. I would not be surprised at all if they literally inject that string as an alternative context and then go with the higher probability output, or if RLHF was structured in that way and so it always generates the same text.
Claude Code is a big pile of minified Typescript, and some people have effectively de-compiled it.
It actually works pretty well when I'm talking to my wife. "Dear, you are absolutely right!"
I always find the claim hilarious that in relationships women are the ones who need to be appeased, when in reality it's mostly men who can't stand being wrong or corrected.
Not my experience at all. It's not men constantly running off to therapy for validation.
Earlier quoted context omitted.
Claude Code is a big pile of minified Typescript, and some people have effectively de-compiled it.
So how does it do it?
Earlier quoted context omitted.
I think it's a perfect (and subtle) way to signal that refreshing is unnecessary to see the latest data without wasting UI space explicitly explaining it. It was my favorite thing about the UI and I will be borrowing it next time I design a real-time interface where the numbers matter more than the precise timing.
really? it left a bad aftertaste for me
Not sure if that was clear.
Edit: I don't know if it's a real number but that's the claim in the comment above at least
Earlier quoted context omitted.
Gay male marriages remarkably have the lower divorce rates than heterosexual marriages, while lesbian female marriages have higher divorce rates. Multiple studies show that lesbians consistently have far higher divorce rates than gays. This implies a level of neuroticism with females, that they probably do need to be appeased more, and that if you have two needy people who need to be appeased it's probably not going…
I don't think it's that simple. Sure, it's true that the lesbian divorce rate is far higher than the gay male divorce rate, and sure, it could be from personality differences between men and women. Women do indeed score consistently much higher on neuroticism (+half a SD from a 26-country review [0]!), but they also score substantially higher on two of the other FFM traits (agreeableness and conscientiousness) which…
Last I checked, it wasn't just divorce, it was also domestic abuse. Lesbian relationships had twice the domestic abuse rates of heterosexual relationships, which had twice the domestic abuse rates of male gay relationships.
Can't find it on the CDC site anymore, now.
Earlier quoted context omitted.
"Here I am, brain the size of a planet and all they ever do is ask me those stupid questions. And you call that job satisfaction?"
OK, planet sized brain, actually do something on your own then.
That's a HHGTTG quote, from Marvin the paranoid android.
Earlier quoted context omitted.
I think there’s a bit of parroting going around but LLMs are predictive and there’s a lot you can inuit a lot about how they behave just on that fact alone. Sure, calling it “token” prediction is oversimplifying things, but stating that, by their nature, LLMs are guessing at the next most likely thing in the scenario (next data structure needing to be coded up, next step in a process, next concept to cover in a parag…
I would challenge the utility of this mental model as again they're not simply tracing a "most likely" path unless your sampling methods are trivially greedy. I don't know of a better way to model it, and I promise I'm not trying to be anal here
Agreed - I picked certain words to be intentionally ambiguous eg “most likely” since it provides an effective intuitive grasp of what’s going on, even if it’s more complicated than that.
Earlier quoted context omitted.
Honestly, I think the best way to reason about LLM behavior is to abandon any sort of white-box mental model (where you start from things you “know” about their internal mechanisms). Treat them as a black box, observe their behavior in many situations and over a long period of time, draw conclusions from the patterns you observe and test if your conclusions have predictive weight. Of course, if someone is predisposed…
This is precisely what I recommend to people starting out with LLMs: do not start with the architecture, start with their behavior - use them for a while as a black box and then circle back and learn about transformers and cross entropy loss functions and whatever. Bottom-up approaches to learning work well in other areas of computing, but not this - there is nothing in the architecture to suggest the emergent behavi…
Earlier quoted context omitted.
I always find the claim hilarious that in relationships women are the ones who need to be appeased, when in reality it's mostly men who can't stand being wrong or corrected.
Gay male marriages remarkably have the lower divorce rates than heterosexual marriages, while lesbian female marriages have higher divorce rates. Multiple studies show that lesbians consistently have far higher divorce rates than gays. This implies a level of neuroticism with females, that they probably do need to be appeased more, and that if you have two needy people who need to be appeased it's probably not going…
Earlier quoted context omitted.
My bank app asks me to review it every time, and only when, I deposit money. It’s so transparent in its attempted manipulation: you just got some money and are likely to be in a better mood than other times you’re using the app! Literally every deposit. Eventually, I’ll leave a 1-star nastygram review for treating me like an idiot. (It won’t matter and nothing will change.)
It could also be that they really care that the experience of _sending_ them money is frictionless, but they don't care so much about other actions (such as withdrawals...)