blinkymach12

"Attention is all you need" is a famous ML paper. Though given the content of the article I don't think the author was intentionally referencing that.

The struggle I found in coding as a CTO was that executive team priorities would come along that would take precedence over my ability to maintain my coding contributions, and in my experience no developer team wants to inherit and maintain code from their CTO. I found myself ultimately more drawn to coding tasks that improved developer experience or validated proof-of-concept work.

I agree with the author that CTO positions are incredibly varied, so I appreciate them sharing what works for them personally and in their organization, even if it doesn't match what has worked for me.

I don't think anything requires a README.md to be monolithic. They often provide the introductory material that you mention here, then link out to other appropriate files for contribution guidelines, etc.

I like this insight. We kind of always knew that we wanted good docs, but they're demotivating to maintain if people aren't reading them. LLMs by their nature won't be onboarded to the codebase with meetings and conversations, so if we want them to have a proper onboarding then we're forced to be less lazy with our docs, and we get the validation of knowing they're being used.

I don't think the bar here is a human level coder, I think the bar is an LLM which reads and follows the README.md.

If we're otherwise assuming it reads and follows an AGENTS.md file, then following the README.md should be within reach.

I think our task is to ensure that our README.md is suitable for any developer to onboard into the codebase. We can then measure our LLMs (and perhaps our own documentation) by if that guidance is followed.

We're in a transition phase today where agents need special guidance to understand a codebase that go beyond what humans need. Before long, I don't think they will. I think we should focus on our own project documentation being comprehensive (e.g. the contents of this AGENTS.md are appropriate to live somewhere in our documentation), but we should always write for humans.

The LLM's whole shtick is that it can read and comprehend our writing, so let's architect for it at that level.

I had the same thought as I read this example. Everything in the AGENTS.md file should just be in a good README.md file.

Thanks! Publication was February 2024.

I'm very much an environmentalist and am very concerned about climate change, and I feel like this article completely put me at ease about sea level rise. I suspect this was the opposite of the intent.

I feel like in comparison to intensified weather phenomenon and especially heat waves, sea level rise sound very manageable.

I also had that impression.

The headline worked for me, and then it sort of teased me along with details that ultimately ended without a conclusion and a feeling of "why did I just read this?"

From memory and a little grepping of the Weekly Kiwi archives, I found: "Project Null Terminator", Aardvark, B??, Caribou, Dingo, E??, Flying Fox, Giganotosaurus, ??