Hacker News Reader

I’m also curious how it really ’weights’ all the instructions coming from main system prompt, my system prompt, skills/plugins, CLAUDE.ms, and nearby code/comments/readme. It clearly should follow some reasonable hierarchy, but because the model itself is so complex, I think (and it feels like) that there is such a mess in its context and reasoning. It deals with it surprisingly well, though, but wonder if it can be done in a more efficient way

For me, Claude usually says ``I don't know'' as first or second answer and stops with this ultra-concise word count of four or less.

(Answer number one before that is usually "I don't have internet access, from memory it is either A or B, but I cannot recall what you want to know." ChatGPT or Gemini can often do the search, while google.com AI assistant or perplexity just tell blatant lies. Copilot.com can do the search, but external links are invalid made-up stuff for harder questions, which seems to be the case 9 out of 10 times.)

Which is great, since it could answer with made-up BS, but does not.

AI, except for doing better web searches for a year now, hasn't really improved for my tasks in the last three years, except for coding. Then again, AGI benchmarks seem to go through the roof only above Sonnet 5 and self-hosting, so perhaps the questions I ask not too hard for long now.

And self-hosting, eve 1bit/1.5bit models are a pondering a little too long to comfortable run in summer, but cheap on the RAM and insanely good at coding since a month now all of a sudden.

I almost wonder if Claude reads that it “keeps responses focused, brief, and concise” and interprets that as built-in behavior and concludes that it doesn't need to spend additional effort enforcing it, just as it doesn't need to expend effort being “accessible via this web-based, mobile, or desktop chat interface”.

Prompts don't matter when you've heavily trained the model for verbosity (because that's what gets you the best benchmark scores).

Claude doesn't "interpret" anything. That's not how LLMs work. They are still sentence completing machines. You give input in, the model network fires the chain that produces the most likely related output. That's it.

I think you might be right, though that this would have influence on other output tokens since it is phrased as a substantive property, rather than an instruction.

I suspect it's related to EU-required watermarking:

> Having said that, in areas where there is an arbitrary choice between particular words or terms within the code, the watermark can be used, such as comments within code. But by definition, it will have a negligible effect on the actual code produced. [1]

I've found that you can reduce the prolixity before (or afterwards) by asking it to use ASD-STE100 Simplified Technical English or ISO 24495-1 after deciding whether a particular comment is worthwhile. (I've since included a standard for "worthwhile" because the clanker doesn't have a good bead on _that_ matter.)

[1] https://www.anthropic.com/news/claude-text-watermark

What definition of "worthwhile" comments do you include in your prompt?

It's not that surprising if we remember that the model is trained to be a generically useful next-token predictor, not necessarily an agent or a chatbot. It needs to know about the environment it's embedded in and what assumptions it can make, and by design the only way to get that information in there is to put it in the system prompt. It's also possible that even if it could figure something out on its own, it's just more efficient to bake it in rather than having it dedicate attention and tokens to it on every prompt.

> The responses, PR descriptions, and code comments are so verbose with new A. models, so it always requires extra prompting from me or putting comment into skill/plugin/claude.md to make them of a reasonable length

I have mentioned this here before, but the majority of my organization has reacted viscerally to this verbosity that LLM-text has been forbidden: in comments, in PR/commit messages, in correspondence, in Jira tickets.

A couple non-coders who want to make PRs without writing the description are now rebelling and saying this can be fixed if we spend our time writing skills for Claude so it becomes readable again.

I wish I worked in your organization. Every time I see the English dialect I call LLM-ese my brain shuts off.

A lot of people are reporting this internally.

The ones not complaining are not reading the text at all, and just forwarding it.

It's insane. But we gotta learn to deal with it in a sane way…

> This is basically just very generic common sense to me

It's important to remember that we are talking about a calculator that doesn't have an understanding of common sense. Unironically, this is common sense.

Yes, but I write this putting an ‘average AI company CEO’ hat on. We hear statements about outstanding intelligence (not just usefulness as a tool, which is no doubt already there), so it’s interesting to see that the authors themselves don’t treat it like that

I think the old Dijkstra quote apples now more than ever:

“The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.”

Whatever these things are doing, it’s not the same as what a person does. Trying to decide if whatever they do fits into the box we label as “intelligence” is completely uninteresting, in my view. What’s interesting is figuring out just what they can do and how best to use them, which sounds like a related question but really isn’t.

Submersibles on the other hand don’t swim we’ve learned

It's because people using this hat are under heavy AI psychosis.