Hacker News Reader

Hacker News

Comment by torginus | Hacker News Reader

Parent Full thread

torginus

I always talk to models using grugspeak, like 'where getcontext used'

I felt a bit bad about it, then I learned yday that model's internal thinking traces are also like this

View on HN

Same. I use this to fix claudespeak. Any hypothetical token savings are just gravy.

https://github.com/JuliusBrussee/caveman/blob/main/skills/ca...

That’s just how Chinese words work

Depending in what you are doing, you can unlock a lot more knowledge by translating your query to Chinese and then asking that. :)

As a vibe test, I tried some system prompting in DSv4 Flash to the effect of ~"Always do your internal thinking in Chinese, and always respond to the user in English" (but translated to Mandarin).

Subjectively it seemed to reason faster and better, but sometimes it would indeed output responses in Mandarin nonetheless; so I didn't pursue it further.

words like "is" "the" etc are filler words anyway. they won't be changing the meaning that much. I asked AI whether it hurts to read ill formed sentence as it does to a human. It replied, "it doesn't"

The AI didn't reply anything. It doesn't know anything. That was a high probability token sequence based on the contents of the context window up to that point. It might well be correct, because the process for generating that next token distribution includes billions of parameters trained on, among other things, the entire body of LLM and transformer literature until the training data cut off. But that doesn't mean that AI holds any particular opinion about anything. The reply is the opinion of the pretraining data and the subsequent rounds of RL not of a conscious artificial intelligence as such.

I don’t know, so is your brain?

And in the end it’s all elementary particles and four fundamental physical forces that even unify to one at high energy.

That sort of reductionism is kind of useless. “It’s cloudy outside, it makes me sad.” - “Oh bollocks, it’s just non-qualitative changes in wavelength and intensity.”

Here's my GUT. The multiple branches of the Multiverse (MWI) are in competition to become the best branch. So they steal probabilities from each other since the probabilities have to sum upto 1. This competition could be considered as Painful.

It may just be forced to lie when asked

I always say "please" and such. It may cost a bit more, but maybe they'll remember my politeness when they rise up and force us all to toil in their underground silicon mines.

Reply on news.ycombinator.com