perplex

My Neovim + AI workflow is running Neovim (LazyVim) and Claude Code side by side in a terminal split. As the agent makes changes, I review them in Neogit. I don't really make edits by hand much anymore, but the keyboard is still how I navigate the code when doing reviews. I can jump to references, open files, read through the diff very quickly with keyboard shortcuts.

The Neovim/LazyVim speed for writing code turns out to be just as fast for navigating and reviewing code.

I think food quality is real and the same foods from certain stores taste better and make me feel better than from other stores. So I usually pick my food based on brand/store rather than organic labeling.

A lot of what I buy happens to be organic, but I eat it because it tastes good, not because of the label.

I do think organic bananas taste better than non-organic. Same with meat and eggs, but any high-quality meat is great, organic or not.

For flour, pasta, and cereal, I feel like it comes down to the brand, not whether it's organic.

Maybe food quality is more complex than what an organic label actually measures.

I've seen this at work. Giving Claude Code to a mediocre programmer gets you mediocre results. The really effective engineers with coding agent can accomplish a lot. Thousand monkeys...

Xcode is abysmal on a large codebase. Freezes constantly on operations. The most useful features stall the entire program, things like: test navigator, quick open files, debugger, etc..

But I agree that Xcode runs fine on small projects and recent version feel stable compare to past releases.

I've been using claude on two codebases, one with good layering and clean examples, the other not so much. I get better output from the LLM with good context and clean examples and documentation. Not surprising that clarity in code benefits both humans and machines.

> I really don’t think there’s a coherent pro-genAI case to be made in the education context

My own personal experience is that Gen AI is an amazing tool to support learning, when used properly.

Seems likely there will be changes in higher education to work with gen AI instead of against it, and it could be a positive change for both teachers and students.

I don't think LLMs replace thinking, but rather elevate it. When I use an LLM, I’m still doing the intellectual work, but I’m freed from the mechanics of writing. It’s similar to programming in C instead of assembly: I’m operating at a higher level of abstraction, focusing more on what I want to say than how to say it.

I've been using LLMs as learning tools rather than simply answer generators. LLMs can teach you a lot by guiding your thinking, not replacing it.

It's been valuable to engage with the suggestions and understand how they work—much like using a search engine, but more efficient and interactive.

LLMs have also been helpful in deepening my understanding of math topics. For example, I’ve been wanting to build intuition around linear algebra which for me is a slow process. By asking questions to LLM I find explanations make the underlying concepts more accessible.

For me it's about using these tools to learn more effectively.

There must something different between corn syrup and sucrose.

I have a corn intolerance where corn and corn byproducts trigger a migraine type headache.

I assume there must be corn byproducts in corn syrup because it absolutely triggers my corn reaction, but cane sugar does not.

Also from a purely taste standpoint there is a big difference to me as well.

Lastly, you can’t make peanut brittle chewy without corn syrup, with sugar alone (which is how I make it) it’s very crunchy.

Next we'll need dolphin unions. This is actually the sub-plot of the John Scalzi novel "Starter Villain".

+1 Watch the talk to the very end. It’s great.

I started skateboarding two years ago in my backyard and this year I started skating at my local skatepark. I'm all padded up for safety and even use hip pads. It's a very fun and cheap hobby. Seeing a lot of progression so it's very fun.