Hacker News Reader

Comment by mras0 | Hacker News Reader

Not sure why you're being downvoted. You need a to know quite a bit of esoteric knowledge to parse this beyond knowing x86 opcodes (even x86 assembly).

It's more or less the same information you get from the intel manuals (specifically appendix 2A of https://www.intel.com/content/www/us/en/developer/articles/t...). There you can also see what e.g. "Jb" means (a byte sized immediate following the instruction that specifies a sign-extended relative offset to the instruction).

One-byte opcodes here differs from 2 byte opcodes (386+ IIRC) prefixed by a 0F byte and even more convoluted stuff added later.

View on HN

>Not sure why you're being downvoted.

I downvote people when they say they don't know what something is when they could have used a LLM to explain it to them.

What if the LLM gives them bad information and they don't know it? I personally would also just ask in a thread than risk the LLM info.

I never punish people for asking a question. It's how you learn!

The link is to an opcode map with strange abbreviations with no apparent explanation. Asking "What am I looking at?" without doing any research (with a LLM or otherwise) is entirely reasonable.

It is entirely reasonable, but these kind of comments are essentially wishing sites could cater to their knowledge level.

It's like complaining that the article is not written in French. It's noise in the comment section of an article. If someone wants such a thing, browsers have functionality to translate pages to French. Not every site needs to have their own French translation to suit such a person.

They were not asking for the website to change; they were asking for context so that they can appreciate the website.

In this case the person was not asking anything. The person was stating they didn't understand. The equivalent in my analogy is a French speaker commenting that they don't understand English without further translation into French.

Geez. I was the first one to comment. It was "This may be great, but... would you please give us more explanations / context." It's not "laziness" but trying to understand how this table is useful / teaches us something. And, to the OP, that a 'typical' HN reader didn't get it.

I know 8008, 8080, z80, 80186, 80286, 80386, 80486, and some fancy opcodes for SSEx. The table still, IMHO, needs further explanation. Some have provided pointers to more info; thank you.

I understand what you're getting at, but in this case even I (who know what most things on that page means) struggle to understand why it was submitted. Are we looking for the 0E opcode? New optimization opportunities?

Genuinely asking, for this post did you click on the link and say "yeah, I got the point" or did you involve an LLM? If you did, what did you ask it? I'm asking because I want to get better at LLM use (Another example post (and prompt) where you've used this, that's also fine)!

I didn't initially use an LLM, but when drafting my original post I did double check that Grok was able to explain it to ensure I want demanding the impossible.

I asked it "Explain the syntax on the page https://www.sandpile.org/x86/opc_1.htm"

So you would rather people ask a machine that is known to be unreliable and have no idea what it's talking about, than ask a forum of technically skilled people who will give them a good answer. That doesn't seem very reasonable to me.

Why's that? Its is most advantageous to ensure that other people are kept in the dark.

If they are willing to pay to level the playing field perhaps it might be worth your while to fill them in. The old scholastic business model — gotta pay to play. But to take precious time out your day to fill them in to your own personal disadvantage...?

In other circles where people have well-rounded feelings you might find someone willing to do it just for the warm fuzzies it gives them. But technically skilled people are generally void of such emotion. That is often what compels them towards technology in the first place.

You realize that LLMs are trained on human discussions right?

If everyone stops asking questions and asks the LLM instead, there is no new training data for future LLMs to learn from. They will stagnate, or consume their own slop, and regress.

Reply on news.ycombinator.com