Live data from Hacker News

Show HN: The load-bearing vocabulary of Claude

louisabraham.github.io

221–230 of 326 posts

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

#222
post #204

Interesting response from Claude, when I attempted to reduce the "load-bearing" in its responses: I added to my global prompt: - Orwell's first rule: never use a metaphor you're used to seeing in print. "Load-bearing", "the crux", "first-class citizen" signal insight instead of showing it. Name the specific mechanism when I asked what it thought of the change, its reply was: The Orwell bullet fights my own system pro…

It's not picking the word, the harness literally told it to plant it.

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

#223
Besides vocabulary I'd also be curious about how it structures sentences.

The "X, not Y" is well known, but another thing that bothers me is "It s no " instead of "It doesn't ".

For example: "the list contains no string" or "it changes no behavior" or "it holds no directory".

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

#224

Earlier quoted context omitted.

I think another classic reference: Jobs saying to the original Macintosh team - "real artists ship"!

To be clear, I am referring to software and shipping as a developer who has finished, more or less, their app. Not that I am against its use, I just never really heard that word being used before, and now I hear it all the time. Thus, what the real issue I have with it is, is because my brain has associated its use with a torrent of crap, ie. AI slop. I hear the word used, and I already have bad feeling about it. And…

imo its a change in definition. Previously to "ship" was a one-time thing that you did for big, highly verified and checked stuff. Physically shipping your software to your user tends to be done after its a product.

Nobody was "shipping" a PR, or a jira ticket previously

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

#226

Besides vocabulary I'd also be curious about how it structures sentences. The "X, not Y" is well known, but another thing that bothers me is "It s no " instead of "It doesn't ". For example: "the list contains no string" or "it changes no behavior" or "it holds no directory".

Yes! This is probably the one thing I want to think about but it requires detecting thise constructs. I think spacy was able to annotate each word with a function, so it should be able to validate known constructs but I need some model to perform unbiased discovery.

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

#228

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…

> the inherent intelligence of the model making its language more intricate and difficult for humans to easily parse?

Humans who are actually well above average intelligence don't write like that simply to signal intelligence (although sometimes they're constrained by style expectations of their communication channels). So I hesitate to accept it as a sign of increasing model "intelligence", either.

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

#230

Has anyone been able to steer Claude so that it doesn't use this kind of vocabulary and super verbose code comments? We use it at work and the language and verbosity has been one of the most annoying things.

I have a non-negotiable rule to start responses with a TL;DR and omit any follow-ups, potential caveats, and "you should know that"s unless they can lead to destructive actions or loss of data.

I also forbid replying with anything besides "yes" or "no" to yes/no answers.

It works, Opus 5 is still super-annoying but this makes it bearable to use.

Post reply on HN