The stupidity that makes depriving one of your senses seem like a sensible thing to do in a busy chaotic environment.

I don’t actually mind people doing that though. What is annoying is the entitled attitude that there should be no consequence for that choice, and everyone else should orbit/compensate around their lack of situational awareness.

Stockholm is a very quiet city, people still wear noise-cancelling headphones all the time.

There’s more than one issue. It’s not wrong to try to solve one of them.

Some people wear them there.

As perfectly captured in "don't _tend_ to ..."

Play. People love to play.

The culturally assigned meaning to work seems more like a social coercion.

If given the choice, including choice in mind, then people will likely choose community and play.

This. So many people are coerced to wear a straitjacket, run the treadmill, and do the rat race, conditioned that "hey work is life, life is work" and is divided into workweek and weekend. For some it may work well, if their job aligns with their interests and passions. Many others are in it with only half their heart. They may show better productivity metrics to the manager class, but what they gain there is lost in 'quality of service' to society. You get automatons at the desk, not interested to handle your edge case. But my, are they 'productive' for the bottom line.

Play is type 1 fun: fun in the moment.

People also love type 2 fun. It's not fun in the moment, but you're happy that you did it.

If your work is type 1, more power to you. A lot more falls under type 2's umbrella. I find writing to be type 2 more often than not. Making complicated designs is often not fun in the moment. I like exercise, but sprint workouts are type 2.

You're forgetting Type 3 Activities, which are neither fun at the time, nor afterwards on reflection.

League of Legends players are very familiar with type 3 activities.

A complete accounting of fun types has to include Type 0 fun as well: fun when it's happening, but not fun later. Drugs, gambling, crime, and most traditional vices fall in this category.

And yet they are a type of fun!

This is not it, though.

This is one contract that mutates.

Other websites have EU terms, us terms, etc and declare which one you are covered under.

To an extend you are likely doing something wrong.

I understand that the natural instinct is to correct the output when you see your agent doing something wrong.

That is not productive.

The instinct should be to tweak the agent to do it right.

At this point I am almost not writing any code in an enterprise code base.

> The instinct should be to tweak the agent to do it right.

I'm extremely doubtful of this. It doesn't save time to tell it "you have an error on line 19", because that's (often) just as much work as fixing the error. Likewise, saying "be careful and don't make mistakes" is not going to achieve anything. So how can you possibly tweak the agent to "do it right" reliably without human intervention? That's not even a solved problem for working with _humans_ who don't have the context window limitations, let alone an LLM that deletes everything past 30k tokens.

Are you seriously interested in the answer, or are you just mad?

I could give you some pointers, but will only type it out if there is a point

Not GP, but I would love pointers on precisely this problem

It is about tweaking inline documentation to make sure that

1. It is not ambiguous 2. It is as complete as possible.

I am surprised that I got down voted for proposing the improve a code base such that agents can run on it as a means to increased productivity.

I'm not touching code. I'm trying out the feature, and there's any number of things to tweak (because I missed some detail during planning, or agent made bad assumption, etc).

> The instinct should be to tweak the agent to do it right.

Ah, yes; must always remember to add "And don't make any mistakes" into the prompt /s

I am not entirely sure what you are referring to.

Improving the agent means improving the code base such that the agent can effectively work on it.

It can not Com as a surprise that an agent is better at working on a well documented code base with clear architecture.

On the other hand, if you expect that an agent can add the right amount of ketchup to your undocumented speghatti code, then you will continue to have a bad time.

Likely historically true, but not anymore.

As a software developer I see that LLMs are better at the "craft" of making software.

Software developers training are overwhelmingly analytical.

Musicians will experience the same. That the quality of Ai generated music is superior. But it will come more as a chock for the reasons you explain.

Musicians are already experiencing this. The likes of Suno are churning out high quality songs with only a minimal amount of prompting material.

One can roughly prototype a song, giving it the structure, melody, harmony, rhythm, lyrics that a finished song might have, upload it and request a cover in a particular style. The output will often resemble a highly competent human performance.

I think the idea that every body are going to build their own SaaS product is likely wrong.

But that is also not the only was to have impact.

Whatbindo think happens is that everybody already building things will reduce or entirely remove their reliance on other SaaS tools.

So retool and other support products are likely dead.

The people who used these products are already more than capable of rolling Auth.

Likely already happening.

To be fair, Gemini did try to get me to buy some nucleo144s recently...

(sure, I was working on something embedded, and asked for a recommendation, but it seemed quite intent that it wanted me to use that specific board)

It is likely not a hoax and likely very intentional.

If you look at the positioning, someone has definitely justified that this is benign and a reasonable place to have an ad added in.

Now, the EU can, using the anti coercion instrument.