Do you have a working example of a skill reducing tokens on repeat tasks? I'm personally seeing the cost of writing and maintaining skills to be much larger than the tokens I'm saving by doing so.

I think an engineer might, but my mother and wife will certainly pick the $5/mo option every time.

I thought similarly to you, until I saw it: https://www.youtube.com/watch?v=abRie4vAvJ4

It almost seems intentionally AI? If anything, if my job at Maccas…ahem, McDonald's (sorry, spot the Aussie) is in marketing, I’d expect to to be promptly fired if this wasn’t expected to pass for anything less than satire.

Do you have children’s names for other restaurants?

Yeah, seeing it just once it looks like an ad with a terrible premise.

It certainly has an AI feel to it though, and I'm sure the more times you see it the more it falls apart.

On 1st watch the part that sticks out is the couple sitting by a window, who seem to be somehow sitting both inside AND outside at the same time.

I still cannot see the bad part

I am legitimately sorry

You have to turn your monitor on, silly!

“a lot of people” - citation needed.

You realize it was a Dutch ad, correct?

I've worked in software supply chain security for two years now and this is an extremely optimistic take. Nearly all organizations are not even remotely close to this level of responsiveness.

Again, that's why LavaMoat exists. Set it up once and it will block many classes of attacks regardless of where they come from.

Post your resume

This is explained here:

> Here's the trick: github.actor does not always refer to the actual creator of the Pull Request. It's the user who caused the latest event that triggered the workflow.

Sorry, what?

Presumably, the original quote that would _not_ stump an LLM is "A father and a son are involved in a car accident. The father dies, and the son is taken to the emergency room. At the emergency room, the surgeon remarks "I cannot operate on this person, he is my son. How is this possible?"

Where the original gotchya is that the Surgeon can be the son's mother or other adoptive parent.

The modification catches the LLM because with the modification, the surgeon could just be the cousin's parent -- father or mother -- so there is no gender/sex at play here but the LLM continues to remark that there is, therefor exposing its statistical training sets.

The original, well-known version of the riddle starts "A man and his son..." so that it appears to present a paradox if your instinctive assumption is that the surgeon must be a man. The op's prompt alters this so that there is no potential paradox, and it tests whether the model is reasoning from the prompt as written, regardless of the presence of the original riddle in its training data.

the unaltered question is as follows:

A father and his son are in a car accident. The father dies at the scene and the son is rushed to the hospital. At the hospital the surgeon looks at the boy and says "I can't operate on this boy, he is my son." How can this be?

to spoil it:

the answer is to reveal an unconscious bias based on the outdated notion that women can't be doctors, so the answer that the remaining parent is the mother won't occur to some, showing that consciously they might not still hold that notion, but they still might, subconsciously.

Thanks for original version AND explanation, I was highly confused by entire discussion.

Still confused how original can be confusing.

Hard for me to believe that even with a surplus of domestic production that comparative advantage of importing still wouldn't be better.

Surprisingly, in this context, I frequently came across interfaces that make it difficult to implement certain features using those libraries. There's not a one-size-fits-all implementation yet.

I think you're going to scarcely find a company that has a direct open source -> hire pipeline. However, one of the most valuable parts of contributing to open source that I have personally found is forming connections and having those connections referring you to companies. I encourage you to find a company + project combination that you enjoy, find ways to collaborate, and make relationships. Doing that will likely yield huge dividends.

Thanks for the advice