Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: The load-bearing vocabulary of Claude

louisabraham.github.io

Post reply on HN
Print view View original

191–200 of 327 posts

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

#191

Post by dare944 »

testdelacc1 wrote: post #190
dare944 wrote: post #140

Earlier quoted context omitted.

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.

All of these phrases existed. Claude didn’t come up with them. The question is whether people are using them a lot more now due to Claude’s influence.

I think it would be fine if more people used "add color to". I think it's a great turn of phrase.

"Load bearing", not so much. Ick.

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

#193

Post by larnik »

sergey_v wrote: post #157
Jordan-117 wrote: post #32

I 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…

It's easy to think "it's not talking down, because I don't understand it, and I'm intelligent". But how is less intelligent being supposed to fully understand a more intelligent one, honestly speaking? All I know is that Claude understands Claude perfectly. I have the common session pause/resume setup that sometimes produces completely incomprehensible markdown files, but a new Claude session picks them up perfectly,…

I treat the Claude output that is hard to comprehend as an encoding/encryption. Claude knows how to decipher it, humans don't. I see this frequently in design docs from inexperienced engineers who used LLMs - they will contain terms (often two words hyphenated) that aren't obvious and should be defined, or simply replaced with simple language. If you prompt claude it is able to decipher and explain / replace this gibberish.

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

#195

Post by pcthrowaway »

Sharlin wrote: post #130
thewebguyd wrote: post #85

Earlier quoted context omitted.

load-bearing was/is used frequently on the ops side of things, I assume the LLMs picked up from physical engineering texts or sysadmin type blogs.

"Load-bearing" is an apt metaphor in the https://xkcd.com/2347/ sense.

Or in the admin handover sense https://lastplacecomics.com/car-jacking/

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

#197

Post by imp0cat »

black_rabbit_ wrote: post #144
Labo333 wrote: post #11

Earlier quoted context omitted.

Author here :) Thank you for the compliment! I did spend a lot of time designing a nice experience on both desktop and mobile. Even the scrollbar to select words was non trivial as I wanted the words to be of different size, yet avoid flickering when scrolling!

You did a fantastic job; very to-the-point with effective visualisations. Kudos! One very minor note: if your scroll device reports pixel-perfect deltas rather than discrete scroll-wheel ticks (e.g. logitech mx master, laptop touchpad, etc), the behaviour in the word search box is a bit weird. Arrow keys work fine though.

On a compatible Logitech device, browsing through the word search box benefits a lot from enabling hyperscroll.

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

#198

Post by throwaway219450 »

stereolambda wrote: post #92
fny wrote: post #3

While 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.

It's interesting that there must be a decision behind that, even if it's just appealing to the RLHF judges for some reason. Maybe there's an intention that if you cannot decipher what the chatbot is saying to you, you will have to ask and burn even more tokens. Naively I would often expect it would talk to me about various niche topics like to a layman, which does occur about some topics an actual normal person would…

I used to assume it was the fault of average human annotators. That the people who are paid peanuts to rank chat outputs preferred the pretentious sounding ones. It wasn’t until quite a bit into the LLM boom that companies started to pay for domain experts. Overt watermarking is another possibility.

I’ve noticed that Sol is pretty good most of the time, but with long contexts it’ll start to devolve into Claudish.

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

#199

Post by sroussey »

user43928 wrote: post #54
sroussey wrote: post #46

Earlier quoted context omitted.

At least "wedged" is a thing i would say on a spinning out of control test that is stuck. "latch" though... not so much. I really wonder if this is the EU AI Act interfering with everything Claude does these days. As a non-EU citizen, I want a version without the rewriting of with watermarking in text.

I don't think so. I understand it's not active yet, and when it will be, it should only nudge the chances between choices that are anyway likely and are already randomized today via temperature. Watermarking is not the reason Claude talks like that.

Oh, it is active, and a pre-release version went out with v5 models.

I understand there are other reasons (overdone RLHF, for example) why claude is wedged into this weird way of writing that takes the joy out of conversing with it, but this is one as well.

The meaning of the words it uses can be oh so close, but the popularity of the words are not, and not in that context -- but the use of these other words changes the context ever so slightly, and then it uses other words where those words would work better.

I had something in code that related to people over time periods, and once it switches to a vacuous word choice, i found it starting talking using all ERP terms. I had to google the whole sentence to understand that, individual words were fine they just didn't make any sense to me.

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

#200

Post by danpalmer »

fnordpiglet wrote: post #175
danpalmer wrote: post #166

The 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.

I think these are more like RL tics caused by over zealous alignment towards specific goals, not all of which are to our benefit. A lot of the language used by Claude now is excusing of responsibility and inducing it to exit loops of work early and sit idle. This, IMO, is a naked attempt to offload load by quieting the models early and escaping from clear work to do. It’s gotten so bad that opus 5 loop escapes even a…

You may be right, but I would push back on near total market capture. I guess it depends which market you're referring to, but even scoping to just software engineering I don't think they got anywhere near total capture. OpenAI has always had a good foothold there, Gemini, while it may be lagging at the moment, had some great results with earlier models that I'm sure have held some market, and that's not to mention the Chinese market.

I think it would be fairer to say that Anthropic held the mindshare in the Silicon Valley style tech scenes around the world and the companies built on that model, plus a substantial portion of other software engineering. Now it seems that's dwindling quite rapidly.

Post reply on HN