Some people "got" LLMs back in 2022, others needed it to evolve a bit.

It's not unlike computers. I started using them back in the 90s and absolutely nobody I knew was interested, while today everyone carries one in their pockets...

Or it could be just Claude CLI doing something very well.

Not they’re all getting incredibly expensive, even the last few startups I worked at were paying hundreds of thousands of euros for services that were total garbage.

Do I really need a crappy 20k/yr app to help me with my 1:1s? Do I really need a 100k/yr clicks counter that requires two devs to keep running and still heavily miscounts the clicks? Do I need another crappy app to manage my translation JSON files?

The original plan was to ship Python. However I found out I can migrate them to CoreML, and now it's a model file + Swift code. I got some massive performance improvements as well.

Of course, this doesn't work at all for non-Mac environments, but it was nice to be able to do it. (Also doesn't solve the duplicate large models problem)

I remember Usenet in the 90s being 50% interesting conversations mostly about niche topics and 50% randomly devolving into flame wars in larger communities.

Even "Eternal September" as a concept was something from around 1993/1994 right?

Same for the 2000s era online-bulletin-board. I often go to thegearpage.net and am appalled at the amount of shilling, dismissals and disrespect, but then I remember that in the 2000s the main guitar forum was Harmony Central, which was mostly kids calling other kids moms names.

EDIT: But coldtea makes a good point about some (IMO) more recent changes: tone-policing, excessive marketing. There's IMO also a different attitude towards curiosity today.

I thought nothing of it until I saw this discussion, so I saw no reason to save/screenshot.

It's ok if you don't believe in me.

Yes! Another crazy thing Claude has been doing recently is treating things like a quiz.

I recently asked about a "90s film that has sepia/b&w scenes (for story reasons), and has one of the ghostbusters actors in it, either bill murray or dan akroyd".

Claude gave a few generic answers and after a couple just went "Ok I give up, what's the answer?".

ChatGPT got it right after a couple messages back and forth: https://en.wikipedia.org/wiki/Rainbow_(1996_film)

(It's not that good of a movie)

The problem here is not doing tasks and outputting garbage output.

On the other hand, that's what a machine would say!

It often start going into circles when you have the chat open for medium-long, and starts getting even easily-verifiable tasks wrong, cutting corners, hallucinating APIs, things like that.

Cleaning the prompt and starting from scratch often does the trick.

Of course someone will arrive and say the problem is my CLAUDE.md or whatever it is.

I'm not gonna argue if you doubt it, I've been training argument dodging :)

People are polarised about how you should talk to a machine !!!

I provided a question, and when given an incomplete answer, I provided with more info.

It refused to accept the additional info due to limited access to Youtube.

There was nothing more than that. There were no expectations.

The hostility and the amount of assumptions here are very strange.

...almost as strange as having a website accuse me of hallucinating a video and trying to gaslight it :D

I use another service for coding.

It's interesting how my experience there is mirrored by the answers here, though!!!