I inhaled Lord of the Rings on first reading. I lived inside it. And it had no illustrations except maps, right? But later when the movies came out they were a big disappointment for ne, they were not the world I had visited. And they were boring. Had I not read the books before, they might have been just fine.

Yeah, the (Peter Jackson) movies were basically LotR seen through the lens of decades of D&D and Warhammer Fantasy, a peculiar aesthetic which of course grew off LotR itself.

I'm guessing that Tolkien would have deeply hated it all with a burning passion.

Couldn't AI write the commit-message based on the prompts-history up till the commit thus making it easier to understand for any future reviewers what lead to and what is in a specific commit?

If it walks like a duck ... AI thinks it is something like a duck.

I think readability is in the eye of the reader. JSON is less verbose, no ending tags everywhere, which I think makes it more readable than XML.

But I'd be happy to hear about studies that show evidence for XML being more readable, than JSON.

I disagree that XML is more readable in general, but for the purpose of tagging blocks of text as <important>important</important> in freeform writing, JSON is basically useless

>But I'd be happy to hear about studies that show evidence for XML being more readable, than JSON.

But I’d be happy to hear about studies that show evidence for JSON being readable, than XML.

XML helps because it a) Lets you to describe structures b) Make a clear context-change which make it clear you are not "talking in XML" you are "talking about XML".

I assume you are right too, JSON is a less verbose format which allows you to express any structure you can express in XML, and should be as easy for AI to parse. Although that probably depends on the training data too.

I recently asked AI why .md files are so prevalent with agentic AI and the answer is ... because .md files also express structure, like headers and lists.

Again, depends on what the AI has been trained on.

I would go with JSON, or some version of it which would also allow comments.

Yes, but what about the "spec-review"? Isn't that even more important? Is the system doing what we (and its users) need it to be doing?

Can you not use it for free?

The harness (OpenClaw) is free, but you have to run a local model or pay for a remote one. Local models just aren't smart or fast enough for good results in this space yet.

Minimax is $10/month. OpenAI/Claude have $20/month. You likely spend more on coffee these days

And you can’t run OpenAi / Claude subscriptions through OpenClaw without violating their ToS. You need to use API keys, which are pay as you go

Good point. If I quit coffee I could easily afford those :-)

It's a bit like saying "Writing English was always the easy part" vs. writing a book that becomes a best-seller or classic.

I think thats a great analogy. There are a lot more people who can dictate a story page by page to a "writing machine" and create a 300 page book than there are who can write a 300 page book of a the same quality without a writing machine.

Same with coding. Most programmers, and writers, are average. They are not doing amazing work. They get paid 80-120k, same as the HR professional, or the account manager.

Creating average work was always relatively easy for writing and coding and is now relatively easy for everyone.

Correct! I’d go further and say typing is the easy part of writing a book, and I absolutely agree with that

I don't think we should pick a winner. When it comes to mathematical answers the best would to pose the same query to all of them and if they all give the same result then our space-rocket is probably going in the right direction.