Claude talks like me. I'm so screwed. I fully anticipate being physically present and verbally saying something and being accused of using AI to say it one day. Nevermind we're in the coffee shop and neither on of us has looked at a screen the entire time. The accusation is coming.
Show HN: The load-bearing vocabulary of Claude
161–170 of 327 posts
Re: Show HN: The load-bearing vocabulary of Claude
#162Claude talks like me. I'm so screwed. I fully anticipate being physically present and verbally saying something and being accused of using AI to say it one day. Nevermind we're in the coffee shop and neither on of us has looked at a screen the entire time. The accusation is coming.
So you're saying you're safe for when the machines take over? :|
Re: Show HN: The load-bearing vocabulary of Claude
#163I really love this. It’s comprehensive, it consolidates the data to the point where the argument effectively ‘makes itself’, and the way it’s presented respects the reader’s time. It also makes for an interesting challenge (for me at least) to try to characterise the subject matter of a language problem so narrowly. No ream of slides. No narrative. Just a lovely big painful conclusion.
> the argument effectively ‘makes itself’ What argument? I don't know what to take away other than "Claude likes certain words". Some of them are kind of amusing, but I'm not convinced the vocabulary is bad or that this is a problem, just from looking at this.
Probably not what the author intended, but to me, this represents a great argument against the somewhat frequent claim that "AI writing patterns reflect human writing patterns". Rather, AI writing is distinctly not human, and is drifting further from human writing with every new model release.
LLMs were not taught to say the phrase "load-bearing seam" from humans saying it, because humans have never said it. It's almost definitely an artifact of post-training and nothing more.
Re: Show HN: The load-bearing vocabulary of Claude
#164Surprised I don’t see footgun. That’s as common as load bearing in my interactions.
No “long pole” either.
Re: Show HN: The load-bearing vocabulary of Claude
#165Earlier quoted context omitted.
I remember asking claude in claude code why the "seams" and it instantly in very fine detail said how it's from a book on working with legacy code so they might be RLHFing on these specific approaches and then it becomes the entire model just an anecdote but I found it interesting how it went full on that it's from that book vs just "it's technical jargon"
AI model does not know special insight into how model itself was trained. All it tells you is it's prediction of expected explanation.
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.
Re: Show HN: The load-bearing vocabulary of Claude
#166The vocabulary truly is load-bearing, without these words the model is less able to think. Where a human can understand a concept without words, an LLM plainly cannot. This is based both on the technological limitations and based on the evidence we see: as these models get better at working they get worse at communication.
Re: Show HN: The load-bearing vocabulary of Claude
#167Was talking about the use of shipped recently, and I was mocked for asking such a crazy question, by freshly self-minted engineers, no less. No wonder they thought it was ridiculous...it had been a part of their vocabulary their entire career. All few weeks of it. I wonder what those guys are doing now. This was about a month ago. Do you think what they shipped ever...landed?
"shipped" was a pretty common term before AI though. It does show as 17x more common on github in this dataset but it was used a lot more in product management than in PRs previously.
Yes. "Ship it! A practical guide to successful software projects" by Jared Richardson, Will Gwaltney, Jr. has had a few printings since 2005.
Re: Show HN: The load-bearing vocabulary of Claude
#168I think you should recognise machine text not only by a list of words, but also by format. Right now, when it handles any complexity of text so well, the only thing that can differ is the structure. Machine text differs from human text in that it is just well structured. It does not allow non-linear narration. And it very often repeats some known social media patterns.
Re: Show HN: The load-bearing vocabulary of Claude
#169I wonder if this jargon is an attempt or strategy to use less output tokens? It sure is annoying.
Re: Show HN: The load-bearing vocabulary of Claude
#170I find Claude language often hard to process and having to wade through these words can be draining. Embarrassingly, I’ve recently caught myself using them in conversations! Do all models have the their own jargon?
I swear claude took a detour recently, its written output has been nearly incomprehensible to me. At first i thought i was getting AI-brained and just lost critical thinking but as i dug into response after response its was just the most obtuse language to explain what was going on. Really mentally taxing to wade through it all day.
It's almost unusable.