Hacker News Reader

Comment by TwelveEyes | Hacker News Reader

I don’t quite think this tracks. Perhaps you want to communicate 1000 bits that are well known and can be referenced with a 300 bit key. Then the LLM can easily retrieve the remaining information. It’s like sending someone a link to the Wikipedia page instead of explaining something yourself.

No, I don’t want to read LLM writing because it is BAD at it. It doesn’t really understand how humans think (because it thinks differently), and doesn’t seem to understand core principles very well (presumably due to the lack of world model), so it can’t write something humans enjoy yet.

View on HN

That's kind of my point. If the 1000 bits are well known, then their inclusion isn't new semantic information. By pasting an LLM's output, you're deciding for your reader that they don't already know that information, and deciding that your LLM prompt is better than whatever they would to to obtain that information if they lack it. IMO, it's much better to give your readers the 300-bit key, and let them decide for themselves if they want/need to get more information, and if so, how.

Why not do both though? I often now write my human summary, then paste in also the content you could get by asking a bot (with markers for which is which). You’re perfectly welcome to ignore the bot text, or ask your own bot, but bots are pretty slow, so I also don’t want to wait for it to “decompress” that 300 bit blob to get the detailed page back. But my human summaries are also only intended to be 50 bits — compressed again to just pass the signal I mean to convey, and not the whole prompt needed to fetch the right info from the right place to substantiate the claim.

TLDR the length was the same curtesy of tl;dr before, just now with a different name.

Mmm perhaps, but I think you normally have an idea of who your audience is. If this was actually how we talked then I would have just responded to this comment with “known-audience rebuttal. Example. Audience knowledge clarification. Example absurdity comment” and let you work it out. I think it’s normally known to you and the LLM and not known to the person you’re speaking to. Speaking like that would just cause confusion and misunderstanding.

> I think it’s normally known to you and the LLM

I disagree. Unless you gave additional information to the LLM yourself, the LLM doesn't know more than your audience does about what the meaning of such a comment would be. An LLM could certainly come up with something plausible, but it wouldn't necessarily be what you intended.

Yeah I don’t think it could decompress that answer, but most articles are explaining something and most explanations have been done before. The LLM would know in that case. I’m simply saying that you can communicate an idea worth any amount of bits with any smaller amount of bits provided you agree beforehand what they mean. LLMs have access to the entire internet, so we’ve had the chance to agree with them what every term means. But the person you’re writing to may have never heard of this, so you’ll have to communicate the full idea first before you can connect it to its small name.

If only that were the HN we comment on. If a post doesn't spoon feed an explanation for an initialism thats the tiniest bit off the beaten path (eg BGP), there's inevitability a comment about how would it kill the author to define BGP?

Reply on news.ycombinator.com