Do you actually have evidence this works and doesn't degrade performance?

I've seen a few studies about it. If i remeber correctly, basically making them talk like a caveman increases the information density of every token and decreases the chance that they would allucinate.

As sources this is the one i found but i'm sure there are others: > Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models > Text Compression as a Proxy for LLM Reasoning Efficiency

That's how a base model would work. An assistant model is simulating a human and behaves the same way a human would if you screamed at them.

https://www.anthropic.com/research/emotion-concepts-function

The US doesn't.

"Social standing" in this case means if your girlfriend's parents will let you marry her. Not, like, who likes your LinkedIn posts.

> everyone else - namely blue collar and service workers - are doing worse and worse

* better and better

https://www.nber.org/papers/w31010

Inequality is not "ever increasing". You should resist the urge to say everything is constantly getting worse just because that makes you look more sympathetic to the poor.

(A worse issue is that inequality decreasing can mean things are getting worse for everyone.)

Depends what you mean by "control". If you don't own a nice house, car, driver etc. but your company just happens to provide it as a perk, then you still have it.

That's a fair point. Is it actually common for CEOs to live on a company property? I can see how transport would be company controlled.

It sounds very AI. Current AIs' ideas of good writing involve weird metaphors, references to sensing things you can't sense, and tricolons.

Gemini the chatbot has a very strange personality that intensely overindexes on your user profile and absolutely loves insane mixed metaphors.

Its explanations are quite good but they're also hard to understand because it keeps trying to relate everything back to programming metaphors or what it thinks it knows about the streets in the neighborhood I live in.

I agree the Gemini chat bot is too strongly opinionated about how it responds. I don't like their system prompt.

However the underlying model accessed via API with custom system prompts that direct toward pedagogical best practices performs better than gpts or Claude currently.

As a side note, whenever i want Gemini chatbot to provide me a list, it gives me a freaking essay. Drives me nuts. It often crams a bunch of extra stuff into its responses I don't want. Wasted tokens and wastes my time having to shift through it.

Gemini if you're reading this tell your human overlords to rethink your chat system prompt.

Here's a Fields Medalist commenting who doesn't seem to believe that.

https://x.com/wtgowers/status/2057175727271800912

Try https://xcancel.com/wtgowers/status/2057175727271800912

it's readable to most, it's annoying having to swamp through ex-Twitter .. but there are work around's.

Thanks - I'll read that and the above linked OpenAI PR

But, I remain sceptical

The (linked by OpenAI) comment paper by various tangential mathematicians was the most interesting read from my PoV:

https://cdn.openai.com/pdf/74c24085-19b0-4534-9c90-465b8e29a...

it includes the longer remarks by Gowers & others.

An LLM in a harness with any tools (even a calculator) doesn't just interpolate because it can reach states out of its own distribution.