There's a pretty big difference between the understanding that comes with reviewing code versus writing it, for most people I think.

Definitely true for me. What’s particularly problematic is code I need to review but can’t effectively test due to environmental challenges.

Thats a tough situation. How do you handle the testing with human code?

Just as poorly.

I think about this a lot, and do everything I can to avoid having Claude write production code while keeping the expected tempo up. To date, this has mostly ended up having me use it to write project plans, generate walkthroughs, and write unit and integration tests. The terrifying scenario for me is getting paged and then not being able to actually reason about what is happening.

Anything bigger in context? Unfortunately - maybe I have bad luck…

But I don’t get how they code in Anthropic when they say that almost all their new code is written by LLM.

Do they have some internal much smarter model that they keep in secret and don’t sell it to customers? :)

>> when they say that almost all their new code is written by LLM.

Kepping in mind they are trying hard to sell their code assistant what else they can say?

Goal is simple: just lie your way forward to the next VC funding round.

I find that writing good tests is my ticket to understanding the problem in depth, be careful about outsourcing that part. Plus from what I have seen LLM generated tests are often low quality.

This is an odd comment on "Hacker" news. There's a joy to be had in making things like this, even though there are better alternatives and it's often a weird thing to do in the first place. I often do not post the things I create here and elsewhere because I dread this kind of feedback. What do you hope OP takes away from your post?

I have noticed something similar. I feel like I have done that so many times for XML files. Perhaps it is re-establishing the settings when any kind of update gets installed.

There were a number of Motorola-inspired ideas that made their way to Dilbert while I was working there in the late 90s.

Hah I love things like this, where the compiler leaks out.

This is true, also for people immersed in this world. Sometimes the dark mode of a site is ass, and it's better to set a preference for that site to use light mode to make it more usable.

No, but the whole article felt definitively AI-generated.

the entire site feels ai-generated

Always good to have a weed puller in your toolshed. A stand-up puller, specifically, that operates as a lever, allowing it to first grab deeply and then through a rotation of the handle it pulls out quite a bit of the root system. A lifesaver if you have a rain garden which is really just a synonym for weed garden.

the link is to a dandelion root system that goes 450 centimeters into the ground, or 4.5 meters / 5 yards.

we'd like to know how much of that weed would your weed puller pull if your weed puller pulled a full pull?

I would not actually like to know that, since such a device seems impossible

Any recommendations for a particular weed puller?

I've never used a bad one, although I wouldn't class any of them as anything stellar. All of them have looked like a snake's twisted tongue.

Using them depends on the delicate combination and application of brute force and technique. If your technique and brute force is up to spec, a crowbar works as a makeshift weed puller.

This CobraHead weeder has worked well for me

https://www.amazon.com/CobraHead-Original-Weeder-Cultivator-...

It's kinda gimmicky but I found this thing on clearance at a local hardware store and it works fairly well (gets most weeds out without me having to bend over, which is nice): https://grampasweeder.com/collections/grampas-gardenware/pro...

It doesn't get everything but I can do more work on the tough ones when so many come right out.

My Fiskars Xact makes me look like a pensioner but it works really well: https://www.fiskars.com/en-gb/gardening/products/weeding-too...

Not that it gets to the bottom of my dandelions ofc, but it sure feels like it does!!

Yeah, this. Each project I work on has it's own markdown file named for the ticket or the project. Committed on the branch, and I have claude rewrite it with the "current understanding" periodically. After compacting, I have it re-read the MD file and we get started again. Quite nice.