"Fuck" isn't there. Did they only analyze "AI" PRs?
Show HN: The load-bearing vocabulary of Claude
131–140 of 327 posts
Re: Show HN: The load-bearing vocabulary of Claude
#132I wonder to what extent this is the result of suboptimal RLHF versus the inherent intelligence of the model making its language more intricate and difficult for humans to easily parse? On the one hand, it's a common trope that highly educated people can talk in a way that's confusing and annoying to regular people who don't know all the jargon. But on the other hand, it's a mark of a skilled communicator to be able t…
My unprovable pet theory is that, especially for writing about technical topics, the RL process has an open-ended way to weight things for quality: textbooks and first-party docs preferred to old stackoverflow answers and obscure blog/forum posts, and so on. The open-endedness of that quality gradient results in something in the RL process (maybe HF, maybe not) massively over-weighting some very small corpus of “quality = near infinite” content. The distribution of quality scores that inform the degree to which RL affects output has some extremely influential outliers, in other words.
Whatever that small corpus is, it contains some very specific grammatical tics, and that’s how we get Claudish.
Anyone who thinks a company/project as big as Anthropic/Claude wouldn’t make such a big mistake should take a look at how Azure cross-account federated login used to work.
Re: Show HN: The load-bearing vocabulary of Claude
#133I once asked Claude to replace “byte-identical” with a simpler word, such as “duplicate.” He refused and said “duplicate” does not mean the same thing as “byte-identical” so it should not be changed. He was very nerdy about it, so maybe that is the right way of his evolution.
Re: Show HN: The load-bearing vocabulary of Claude
#134Earlier quoted context omitted.
I'm not even sure a PhD helps. It just overuses jargon that has NO meaning. Sometimes, it actually hand waves too much as well while trying to dumb down stuff for you. I am not sure whether it's a consequence of learning to reason from its traces or some RLHF that trips it into using weird terms to sound smarter to the humans who rate it.
PhD was a joke. My intuition is that Claude is trained to communicate to itself while coding. You see this in how bizarrely granular it is when explanation prior work, you also see this in the comments it leaves behinds.
Isn’t that basically what thinking mode is?
Re: Show HN: The load-bearing vocabulary of Claude
#135Sounds like this is that watermarking at work.
Re: Show HN: The load-bearing vocabulary of Claude
#136While Claude's style is obnoxious, I'm more frustrated by its inscrutable explanations. You need a PhD to understand its explanation of a code snippet.
Sometimes I can't even tell if what it's saying actually makes any sense to someone who understands all the terms its using, or if it's just throwing together words in a way that only make sense to its own model of language.
> or if it’s just throwing together words in a way that only make sense to its own model of language.
alwayshasbeen.jpg
Re: Show HN: The load-bearing vocabulary of Claude
#137Earlier quoted context omitted.
In the enterprise, we are already adopting them. “Seam”, I term I’d never heard used before, is now not only our defacto way to describe the boundary between systems/workflows/components, it is encoded into our organizational roles and responsibilities descriptions. I am the proud owner of several seams, and am considering giving them person-names. The empty space between my inventory APIs and their clients might be…
I believe the term "seam" came from Michael Feathers' "Working Effectively with Legacy Code": “a seam is a place where you can alter behavior in your program without editing in that place”. https://martinfowler.com/bliki/LegacySeam.html Claude is using it a bit liberally, but not totally incorrectly.
I've associated it with the concept of "carving nature at the seams", except that I just realized that in the standard phrasing it's actually "at the joints", not "seams".
Re: Show HN: The load-bearing vocabulary of Claude
#138The README of this project is very ironic. https://github.com/louisabraham/load-bearing/blob/main/READM...
Re: Show HN: The load-bearing vocabulary of Claude
#139While Claude's style is obnoxious, I'm more frustrated by its inscrutable explanations. You need a PhD to understand its explanation of a code snippet.
They just addressed this with "Output styles" https://code.claude.com/docs/en/output-styles
My experiments with output styles have not been sufficient to keep the model in check. It still spits out incomprehensible gibberish and load-bearing-isms.
Does anyone have an output style nailed down that actually works? If so, please share!
Re: Show HN: The load-bearing vocabulary of Claude
#140I was pleasantly surprised when I attempted to scroll down and realized everything the author wanted to present fit on-screen. It's almost ironic that this site is able to make such an obvious, compelling presentation without being overly verbose or complicated (something which LLMs have a hard time doing). I wouldn't read TOO deeply into what is being presented, but the author has done a good job to not inject their…
>I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs I'm already seeing it. A coworker said something like " added the color to the ticket here" meaning that someone added details to a ticket. I've started seeing Opus 5 talk about "hermetic testing" when it just means "unit testing", so I hope that doesn't catch on...
The idiom "added color to" as an expression of adding detail or nuance to something goes back much further than the AI era. I've certainly used it at various times in my career spanning 4 decades now.