If you’re familiar with the way in which documentation artifacts like this fall out of a Claude project, you will recognize that every place where Claude says ‘this changes everything’ or ‘this is the load bearing insight’ most likely resulted from a human looking at what Claude had done, and redirecting it towards a more fruitful line of inquiry. When Claude gets ‘excited’ about a thing like ‘we figured out which clock measurement approach helps us actually optimize performance’ - excited enough to explain it in this level of detail - it usually results from the user pulling Claude out of a rabbit hole where it was going about things the wrong way.

I think you severely lack in domain knowledge if you think “nothing else than a bit of prompting went in to this”.

This sounds like you have only had a superficial contact with LLMs. They do a lot of mechanical work, but "a bit of prompting" is not how they are used for something like this.

"A bit of prompting" is subjective, and can indeed take a lot of work to craft accurate prompts which produce genuinely useful output.

How about the desire to steer LLMs to a point of their choosing? LLMs wouldn't do this by themselves...

I have a lifetime pass as well, but switched to Jellyfin years ago.

The app for public transportation in the Stockholm region give real time location updates for its busses, and station-to-station updates for tram and commuter trains. With the constant delays for the operator in my area it is invaluable for catching busses.

My guess is that the whole project including the selection of chips was made by an AI.

My guess as well. I don't like it when humans silently pass off LLM writing as their own.

I also don't like it when humans silently pass off LLM work as their own.

Prompting is not the same as doing the work. There are ways to genuinely collaborate with LLMs, but if someone silently takes full credit for work generated by LLMs, my assumption is they probably vibe coded it.

Plus, I spend my free time expending effort to consume human generated content. I’m okay with slop someone pays me to deal with, but don’t expect people to read your hobby related post when you couldn’t be bothered to write it.

A bunch of us old salty sailing nerds were actually discussing Decca Navigator System¹ the other day that was still very present in the 90s on the ships we were sailing. Now all replaced and removed.

https://en.wikipedia.org/wiki/Decca_Navigator_System

Oh, wow! That seems to fill a gap below LORAN's range, and far exceeding its accuracy. I never heard of it before!

You should.

This describes how you turn off telemetry: https://github.com/microsoft/intelligent-terminal/blob/main/...

This kind of data was shown by late Hans Rosling and his foundation Gapminder¹. He gave a Ted talk² about similar subjects as well, and I find him an excellent lecturer.

¹ https://www.gapminder.org/

² https://www.youtube.com/watch?v=hVimVzgtD6w

But you can go 1500 miles on a full tank, so with electricity you have to account for three times as many vehicles as well (given the stated range is correct)

300 miles between charges if you are limited to a 30 minute charge, but semis probably refill much more often than every 1500 miles, particularly since they are required to stop every so often anyways.

What did you do to start getting traction for senior positions? You were struggling in the beginning of the year.

I've never had a problem getting contacted. I've done some self reflection, and practice and now I'm much better able to communicate technically. It also helped that my last project before I was laid off was pretty wide reaching and impressive and being able to talk about that has made things a lot easier. I still haven't gotten a job I want, so I don't have a lot to offer you, but I'm getting better at interviewing.