fergonco

Wait, Being "very rude" to an LLM gives you 4% accuracy boost.

“Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy”

By Om Dobariya and Akhil Kumar (Penn State University), October 2025.

Prompt tone Accuracy Very polite 80.8% Polite 81.4% Neutral 82.2% Rude 82.8% Very rude 84.8%

A modern chess engine would definitely have defeated Kasparov in 1996. It would have had a database containing all the games, particularly that strange game against a computer nobody knew anything about, which seemed to be able to anticipate all of Kasparov's moves.

Then you get exposed to a supply chain attack.

Then you'll turn on the oven and the ship will start driving in circles.

> Oh, you're absolutely right. I shouldn't have relied electricity usage to encode the production system signals.

For a world. A world some people will not be part of.

When I tried pi.dev (I only used chatgpt before) and told it "add all this scripts I developed over the last couple of years to automate my job as skills".

I love to automate things in bash scripts and these llms just can use them very effectively. It was also surprising how they derive knowledge from those scripts. If you get A from a B uuid, they kind of get the relationship. I am super vague in my request and this thing knows what I am referring to. After some months it's still mind-blowing.

> "Don't use a LLM for that part, it won't be reliable enough".

You should now ask if the LLM is reliable enough when it says that.

Jokes aside, how is this a major step he is missing? He is using those skills to be more efficient. How important is going against agentskills.io guidance?

I have some bash_aliases and scripts.

The king of all alias is fixup, which commits everything and fixes up the commit with the previous one.

Another script just goes over the changes and allows me to add/skip/restore.

Then I can pipe the log to another script that will analyze tags and tell me what is not yet in prod.

cli is hard... but it composes. I want to know that CLI as well as possible. And I don't want to start from scratch each few years with a new UI / concept.

In my country, "hard lines" are next month's "soft lines". So any system that requires those is a problem.

Rough numbers look good.

But the hyper specialized geek that has 4 kids and has to pay back a credit for his house (that he bought according to his high salary) will have a hard time doing some gardening, let's say. And there are quite a few of those geeks. I don't know if we'll have enough gardens (owned by non geeks!)

It's like cards are switched: those having the upper socioeconomic class will get thrown to the bottom. And that looks like a generation lost.

That XKCD is very funny. BTW:

> You are pointing to Waldo on a page... on a specific date. Because of tectonic plates movement.

> If the surgeon were the father of the man (the one who died), then the cousin couldn’t be his son (unless there's some very unusual family structure going on involving double relationships, which riddles don’t usually intend).

> Therefore, the only straightforward explanation is:

> The surgeon is the cousin’s parent — specifically, his mother.

Imagine a future where this reasoning in a trial decides whether you go to jail or not.

> will nonetheless make people's lives better

Probably not the lives of translators or graphic designers or music compositors. They will have to find new jobs. As llm prompt engineers, I guess.

We will always need to work in the fields. With agricultural machinery we'll be doing way more than we were before.

if the amount of new offer is not paired by demand, there will be pain.