It can't hurt to make a sentence or two about assumptions.

Like "This manual assumes that you have a Linux/BSD, a C compiler, GNU Make, and a text editor".

Ideally those are free and open source

That isn't enough, who pushes code and repos location is also relevant.

Are you proposing forks of existing languages but in gitlab, and only european can approve PRs? Or a new language and OS? How does that work in practice when open source is public and users can have VPNs?

Yep, security and digital sovereignty required control of the whole chain.

See how other economies are doing it.

Example,

https://docs.github.com/en/site-policy/other-site-policies/g...

https://go.dev/blog/hello-china

The bulk stockholders of GitLab are:

  - Vanguard
  - BlackRock
  - Google Ventures

Why is that relevant?

Bill of materials, digital sovereignty and attack vectors, see xz attack.

How's the caching? I have 99.5% cache hit rate with deepseek when using their own API, it's dirt cheap.

By asking the AI, which will then go "you're totally right to question that, Markus! Here's a thorough, error-free version:"

But the image isn't a photo of the result. It's an unrelated image that vaguely looks like what you could make, with a different recipe, and with some skill.

How would a photo of the exact recipe differ? Is this not close enough for 80% of the value. It is similar to Pinterest boards imo.

Turkey, roast beef. It’s meat, isn’t it? Close enough.

The main pic looks like a classic British leg of lamb. So what’s your point? Why post such low quality slop?

As I said I can see the value in this similar to Pinterest boards. It is directionally correct and serves most of the value that a picture does. No perfect but probably close enough for the general audience.

> do prefer cookbooks with pictures

Yes, pictures OF THE FOOD. Not unrelated pictures of another lamb-roast made with another recipe.

Good cookbooks do proper food photography, of the food made with the recipe. That's what sets them apart from slop, be it human or AI slop, cook books.

What another recipe? It could just be a physically impossible to recreate lamb roast (Probably not the case in this marketing example though).

Why is it impossible to create? Are we talking about some meal that King Richard I had (https://en.wikipedia.org/wiki/The_Forme_of_Cury is the oldest cookbook I'm aware of which covers meals Richard II would have eaten), and thus we can only guess? Are we talking about the long extinct dodo bird (I'm not sure if humans ate them), cave bear (I've seen it claimed humans hunted them to extinction, but better sources say it went extinct before humans), or something else that we can never make?

For almost everything else we can create them - just give a reasonable cook a kitchen and the ingredients and they will do it. For a picture we then have an artist do preparation to make it look good, but they should always start with the real dish.

Recipe photos make sense when they are the result of someone executing the recipe, down to the color on the lamb, the consistency of the sauce, etc.

That's never, ever the case with the AI generated ones and makes them useless.

I pivoted to using -- or --- instead, shows I'm not a bot and has the same effect.

Wait, am I missing something here? Is this just

> you stupid silly human, instructions are hard! Who can read "fold this" and "fold that", when you can instead have interactive short-form content with music and smileys to keep you entertained while you offload all the thinking to AI?

... as a service?

Am I crazy for saying I like codemode? It reduces the amount of turns by about an order of magnitude.

not at all, it's nice! solves the composability problem while keeping a trust separation between harness/ai bash calls.