arijo

Even if you don't like Huberman, it's very worthwhile to learn from someone like Hyman.

The post is about Mark Hyman not Huberman.

I prefer fringe than stupid.

All sweeteners are considered harmful.

Please watch the video:

https://www.youtube.com/watch?v=Kkyv1o8Xp_M

Perhaps that was true 50 years ago, but in an increasingly complex technological world, problems simply cannot be solved without increasingly advanced engineering skills.

You can create a timer with one transistor and an LC feedback loop.

Almost all civil, chemical, electrical, etc., engineering emerged from a practice-first, theory-later evolution.

How many thousands of lines does your AI-generated frontend code have?

Do you have to maintain the code?

Everyone knows that to understand metabolism you should use a parser.

I've already tried Paul.

Check my previous submission.

I realize now my comment was dumb.

Thanks for the correction.

Many chronic illnesses are currently being researched as a KD treatment target.

Continuous ketones measurement is a big deal.

You probably can use these physics to measure many other molecules in a continuous non invasive way.

This will be a revolution in personalized medicine.

Ketones next please.

Wouldn’t a digital servo mitigate the problem?

"So what kind of programming work would be the opposite of this?

* Problems are ill-defined and poorly-scoped

* Solutions are difficult to verify

* The total volume of code involved is massive

In my view, this is describing legacy code: feature work in large established codebases."

If you have used cursor.ai to try to create a moderately sized project you'll see this happen even with newly generated code.

In my experience, if you limit yourself to generate not well thought through prompts and do not work on getting a deep understanding of the generated codebase, the LLM will start duplicating the same code flows in different ways, many time forgetting some of the behaviour already implemented.

Kind of like having dozens of developers working on the same codebase clueless about what each other has done and re-implementing the same functionality until the code turns into a pile of spaghetti code.

It can be done but:

* You must have a deep understanding of the code

* You need to think hard about what you are doing and give very detailed instructions to the AI

It works for trying a quick prototype but when moving on to production grade code you need to slow down and "program" step by step providing precise instructions as you go.

You'll have to design the changes to the minor detail and then you can let the AI do the grunt work.

It's like programming without coding.