The Xcode 26 System Prompts collection contains a couple of chat templates, but more interestingly: typical LLM-targeted documentation of new-ish technology to prime their context for stuff that’s not well-represented in training data.
For example, ever wondered when to use the new InlineArray? See Swift-InlineArray-Span.md
When to Use InlineArray
InlineArray is ideal for:
- Performance-critical code paths
- Fixed-size collections that never change size
- Avoiding heap allocations and reference counting overhead
- Collections that are modified in place but rarely copied
- Embedded systems or low-level programming
Not suitable for:
- Collections that need to grow or shrink
- Collections that benefit from copy-on-write semantics
- Collections that are frequently copied or shared between variables
That is a very good summary that is painfully absent on the InlineArray API docs. As a Swift veteran, you usually look for a Swift Evolution proposal for the new tech then an try to find out there what this is all about.
Which is to say: I don’t mind quick summaries for busy developers like these!
The collection also has docs for 3D charts, VisualIntelligence (I didn’t know that framework existed!), and UIKit Liquid Glass guides and AttributedString tutorials.
These documents are probably not written by a human, or team of humans, because of inconsistent tone and all. So I’d wager they were LLM-generated themselves. I do hope they were edited for misinformation at least!
If you use agentic coding tools, it’s sensible to copy Apple’s docs into your setup. For Claude Code, you’d drop these into a docs/ folder somewhere to look up, but then you need an index to tell Claude to look there. Per project, that can get repetitive, and as a global setting, it can pollute your context. So maybe a clever solution would be to use ‘formalized’ Skills like Antoine van der Lee’s SwiftUI Expert Skill that is available in Claude Code as a plugin to bundle everything.
Thanks Joachim for sharing the link on Mastodon!
Last Saturday was Global Day of Code Retreat (GDCR) and one challenge session was to only use AI with prompts to implement the Game of Life rules.
Folks who don’t use LLM’s a lot tried to describe the rules to the LLM in their prompts – while others knew that the rules are well-known and that the LLM could regurgitate them based on training data easily.
Continue reading …
Claude Code can commit for you. By default, your name will be associated with each commit, and Claude Code includes a “Co-authored-by:” line, and also an Emoji line that says the commit was written by Claude. (You can turn the Emoji off.) However, if you hand off git commit to Claude Code, it’s possible, maybe even likely, because you want Claude to summarize changes that you did not come up with.
Continue reading …
Over on Hacker News, under the title “We can’t circumvent the work needed to train our minds”, my pal Sascha’s post on Zettelkasten.de became the top post yesterday. The original title is “The Scam Called “You Don’t Have to Remember Anything””.
Something resonated with the tech community there, so I figured you might want to check out the post as well.
The 150+ comments went into all kinds of directions from a first screening. We’ll discuss this further in a couple of days. For now, enjoy reading Sascha’s post.
Nick Bergson-Shilcock of Recurse Center, Developing our position on AI (Emphasis mine): We chose at the outset to limit our focus to the personal and professional implications of LLMs on Recursers, since that’s what we’re knowledgeable about. You won’t find positions or pontification in this post on energy usage, misinformation, industry disruption, centralization of power, existential risk, the potential for job displacement, or responsible training data.
Continue reading …
In New Junior Developers Can’t Actually Code, Namanyay argues that StackOverflow would teach you something, while AI is all about speed. The graph Namanyay shared is this: Side note: Do you remember when StackOverflow was strongly associated with copy-paste-programming without understanding, and that Real Programmers™ read manuals and books instead?
Continue reading …