[saulpw]

That "a good model (if you know how to operate it well)" is doing a lot of lifting. To be sure, there are a lot of bad books, and you can get negative advice from them, but a book has fixed content that can gain and lose a reputation, whereas a model (even a good one!) has highly variable content dependent on "if you know how to operate it well". So when someone or some group that I respect recommends a book, I can read the words with some amount of trust that the content is valuable. When someone quotes a model's response without any commentary or affirmation, it does not inspire any trust that the content is valuable. It just indicates that the person has abdicated their thought process.

[simonw]

I agree that quoting a model's answer to someone else is bad form - you can get a model to say ANYTHING if you prompt it to, so a screenshot of a ChatGPT conversation to try and prove a point is meaningless slop.

I find models vastly more useful than most technical books in my own work because I know how to feed in the right context and then ask them the right questions about it.

There isn't a book on earth that could answer the question "which remaining parts of my codebase still use the .permission_allowed() method and what edge-cases do they have that would prevent them from being upgraded to the new .allowed() mechanism"?

[theamk]

And as long as you don't copy-paste its advice into comments, that's fine.

No one really cares how you found all those .permission_allowed() calls to replace - was it grep, or intense staring, or AI model. All that matters is you stand behind it, and act as an author. Original post said it very well:

> ChatGPT isn’t on the team. It won’t be in the post-mortem when things break. It won’t get paged at 2 AM. It doesn’t understand the specific constraints, tech debt, or your business context. It doesn’t have skin in the game. You do.

[tensility]

Further, grep (and any of its similar siblings) works just fine for such a task, is deterministic, won't feed you bullshit, and doesn't charge you tokens to do a worse job than existing free tools will do well. Better yet, from my experience with the dithering pace of LLMs, you'll get your answer quicker, too.

[000ooo000]

>There isn't a book on earth that could answer the question "which remaining parts of my codebase still use the .permission_allowed() method and what edge-cases do they have that would prevent them from being upgraded to the new .allowed() mechanism"?

You're so close to realising why the book counter argument doesn't make any sense!