A lot of these “Claudeisms” are simply jargon I’ve seen or heard firsthand myself while working at tech companies. I don’t think it’s limited to Claude either; I’ve seen Codex use load-bearing and many of these phrases as well.
I think using agents is just like speedrunning the whole experience of working with technical coworkers. Whereas you might have had a few coworkers at your company who used some of these phrases regularly, you now have a “coworker” who uses all of them regularly at a much faster pace.
Everyone has their own distinct mix of jargon and uses some words more or less than others, but now it's as if you have 1000 coworkers who are all the same person, and talk the exact same way, and it just so happens that their writing is grating to read. It also doesn't stop when you log off for the day. The same guy follows you home in ad copy, message board comments, spam, and in some cases even the correspondence of your loved ones.
I like to imagine that there's this one employee that oversees RHLF, who has a particular style of writing, and that got so ingrained that it's just them x1000.
I checked this, and Claude says "it's a real term of art from Michael Feathers' Working Effectively with Legacy Code (2004), where he defines it as a place you can alter a program's behavior without editing in that place."
While I agree the model doesn't have insight into how it was trained I do think the history of the term itself is interesting.
yeah but I didn't prompt it in a way where I tried to get such an answer, it gave an entire boilerplate rundown just from like me asking "what's up with the 'seams'?"
I might be wrong, but usually it'd be a lot less deliberate, and at least in my mind it wouldn't be surprising if they were heaving training these on these specific "best practices" books/methodologies and thus picking up lingo from them
Those books are definitely in the training set if the model can mention them, but why exactly these terms are so commonly used is not necessarily because the book is in the training material. The model does not itself know how its trained.
The jargon isnt even the worst part. The phrasing is just downright incomprehensible sometimes. And its not even "academic". It's just extremely awkward, bad writing. And it is much worse than say Opus 4.6-8.
Actually I have found the copy that Claude Design spits out is way better than using the same model directly. I have no idea why. It has its flaws but it sounds like it's written by a human who uses derivative language. But usually the models just soudn incoherent.
> A lot of these “Claudeisms” are simply jargon I’ve seen or heard firsthand myself while working at tech companies.
---
The difference in distribution between how often LLMs use them and how often people use them in PR descriptions is almost the entire content of the link.
I built a macOS terminal (libghostty wrapper) that runs iOS simulators (and mirrored physical devices) in a Metal-rendered pane inside the terminal.
It works with standard tooling: for example, if anything in one of its tabs runs `xcrun simctl boot`, the simulator just shows up as a pane in that tab. There's a CLI for the things simctl/devicectl don't cover: taps, gestures, rotation, accessibility tree, etc.
- https://github.com/sethdeckard/atria : TUI for managing multiple AI coding agents that doesn't force a particular workflow on you. You can use tmux, the built-in PTY, or terminal integrations with iTerm2, kitty, or WezTerm.
- https://github.com/sethdeckard/atlas : TUI and CLI (also works as "cd launcher") that creates a smart, automatic map of every Git repository under your projects root.
I built a tool that lets you keep your existing tmux workflow and adds a simple dashboard for monitoring and discovering agents inside tmux: https://github.com/sethdeckard/atria
It supports tmux, but you can use it without via embedded terminal. It also has native integration with a few select terminals that expose the right kind of APIs.
Installs as single binary (written in Go) with no external dependencies.
All the democrats who ran with a candidate who couldn't convince other independents to vote for Harris, or convince all the potential voters who stays home to come vote are also to blame.
Would I have voted for a Democrat or a Republican if they ran the "right" candidate? I suppose anything is possible, but given the history, I would consider that to be very unlikely.
I'm focused on harm reduction - there was no credible non evil candidate on the ticket in 2024. I don't like either of them, but only one of them was whipping up a frenzy to disenfranchise my friends and cut them off from society on a fundamental level, and the other was not.
For sure and the Mac Mini M4 Pro with 64GB of RAM feels like the sweet spot right now.
That said, the base storage option is only 512GB, and if this machine is also a daily driver, you’re going to want to bump that up a bit. Still, it’s an amazing machine for under $3K.
I think using agents is just like speedrunning the whole experience of working with technical coworkers. Whereas you might have had a few coworkers at your company who used some of these phrases regularly, you now have a “coworker” who uses all of them regularly at a much faster pace.