Live data from Hacker News

Show HN: The load-bearing vocabulary of Claude

louisabraham.github.io

111–120 of 328 posts

Re: Show HN: The load-bearing vocabulary of Claude

#111

Earlier quoted context omitted.

I don’t think they’re “talking down”. If anything - it’s way more difficult to distill something into a genuinely easy to digest format. I personally think that they aren’t immediately capable of this, and so we get word salad instead. Extra prompting required to strip extraneous prose out. Maybe I am dumb and it IS talking down to me, but there have been many occasions where I’m reading AI generated docs / plans and…

It doesn't seem like word salad as such. There's normally a coherent point expressed, it's just obscured by circuitous sentence structures, unusual word choices, "verbing weirding nouns", metaphors, etc. Could be a result of training that rewards novel/surprising language, but it also feels like it could be an artifact of models imperfectly compressing high-level multidimensional reasoning into language that's easy f…

Or, maybe they are dumb using smart words to sound smart in RLHF.

Re: Show HN: The load-bearing vocabulary of Claude

#112
post #45

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 phras…

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.

Re: Show HN: The load-bearing vocabulary of Claude

#113
so the real turning point for Claude is around April, which is Opus 4.6/4.7, which is right around the point where I personally started thinking Claude was getting different in a way which feels worse and is more awkward to use. It's better but has lost something that made it feel better.

Re: Show HN: The load-bearing vocabulary of Claude

#114

Why are people getting so hung up on the "load-bearing assumption" turn of phrase that Claude uses? I get that it becomes cliche, but it is also a rather semantically dense way to communicate an idea that a lot of people run into.

That's the problem for me: "semantically dense". Sometimes a single paragraph is filled with several of this expression, one after the other, and there's a real mental effort to get what Claude is saying.

Re: Show HN: The load-bearing vocabulary of Claude

#115

To all the people in the HN comments saying negative things about Claude: why don't you just use other models instead?

For me, there are two reasons: it’s what my work provides, and for some tasks, I want the absolute best model for coding.

Having said that, I just subscribed to ChatGPT yesterday, as I've become impatient with Claude for a text-dense project I'm working on.

Re: Show HN: The load-bearing vocabulary of Claude

#116
post #39

Earlier quoted context omitted.

ItMs because Claude sprinkles these words as flavoring without aiding understanding. It feels like Claude thinks of metaphors that don’t actually mean anything (or maybe only makes sense to itself).

I don't understand. Does the metaphor "load-bearing assumption" not actually mean anything to you?

"Load-bearing" is maybe not the best example, but Claude uses these anthropomorphized decorative synonyms everywhere. Claude's structs don't have fields, they _carry_ them. Its programs don't log, they _narrate_. Its arguments are not provided on the command line, they _ride_ it. Its modules don't depend on other modules, they _sit_ on them, etc.

Re: Show HN: The load-bearing vocabulary of Claude

#117

so the real turning point for Claude is around April, which is Opus 4.6/4.7, which is right around the point where I personally started thinking Claude was getting different in a way which feels worse and is more awkward to use. It's better but has lost something that made it feel better.

Is it actually better though? Can you even measure it? Unguided, Claude will just produce mediocrity which by its own existence becomes almost worthless, and the newer versions become increasingly difficult to guide while also being obnoxious to read. If I did not have to interact with it, it would not be a big deal, but then also I could not get value out of it.

Re: Show HN: The load-bearing vocabulary of Claude

#118
post #21

Author here! Grateful for the kind words, human communities like HN really hit differently when you spend the whole day chatting with sycophantic and bullshitting agents (including to make this page). I'm currently adding a search bar as well as increasing the data to 1000 PR per day. A nice thing that is not obvious on the main page is that the dataset and analysis are updated daily using Github Actions (at least wh…

Great work, thanks for sharing!

The design is really impressive. Beautiful and dense, yet very understandable. How did you come up with this particular design? It's really nice and everything fits, the colors, the layout, all of it.

Were you inspired by anything in particular? I feel like this reminds me of something, but I don't remember what exactly.

Post reply on HN