Comment by robwwilliams | Hacker News Reader

Comment by robwwilliams | Hacker News Reader

Parent Full thread

Too simple, too dogmatic at the start and at the end (“don’t use LLMs” and “then they are poison”). The middle section is all good.

Writing with a LLM is a boon if you are trying to write while mastering a new field. Imagine a neuroscientist entering robotics or an electrical engineer trying to enter the field of neuromorphic systems. In these cases a human will need help from an LLM to think and write more deeply AND broadly. I sure do.

You could object that this form of human-LLM collaborative writing is just for one reader; the writer. True at the start but not true toward the end.

I do agree that even the frontier models do not touch a really strong human writer. Way too much gimmickry. They do not yet match individuals such as Leslie Lamport, Terry Winograd, John MacArthur, Richard Rorty, Humberto Maturana, William James, Rodney Brooks. They don’t have the depth of understanding to simplify. But give them a few more years and excursions in the real world and a concept if “now” and the situation may improve.

I often ask Fable and Opus to explain difficult topics to me as if I were the canonical dog Rover. It works.

No, you need to learn the new field you’re entering enough to write about it. Having incomplete knowledge and writing for others utilizing an llm that you do not know enough to fact check is about the worst way I can think of to use an llm for writing.

100% disagree. The more you don't know an area, the more LLMs will lead you astray.

Explaining difficult topics or summarizing to you is fine. But that's a world of difference from having an LLM write for you. You THINK the LLM is helping you write above your level, but that's because you are not in a position to tell it's bad.

Actually I am in a very good position to tell. And who said “write for you”? How about “write with you as a collaborator?”.

Writing is a form of thinking and writing with an LLM makes the argumentation, discussion, and progress toward goals faster and often better in my situation.

I am stating an opinion based on 2.5 years of intense interactions and writing with Anthropic models on a difficult topic related to asynchronous computational systems.

Background: I am a neuroscientist and behavioral biologist (45 years of experience) who understands the biology of behaviors fairly well but I need to translate this background into hardware architectures that get beyond current asynchronous system (e.g., this recent neuromorphic paper in Nature Communication by Li et al., 2025, A deterministic neuromorphic architecture, doi.org/10.1038.s41467-025-65268-z).

Working AND writing with Opus and now Fable has been a blessing of sorts.

Maybe don't write about something you don't know?

But I want everything and want to do no effort for it

A person isn’t becoming a master in the new field if the LLM is doing all that for them.

New areas are where it is most dangerous to use an LLM, as a person can’t tell when it doesn’t align with their views (because they don’t have any yet), is misleading, or flat out wrong.

If I want to know what an LLM thinks, I’ll ask an LLM. If I’m reading a paper from a human, it’s, because I want to know what that human thinks. If they need the LLM to fill in the gaps in their knowledge, then they don’t know enough to write about the topic yet. Doing that work to write something themselves could help move them learn enough to write something that is hopefully worth reading.

A more facetious way to put "don't use LLMs": share your input prompt. The people who don't want to read LLM output won't have to see it, and those who do can enjoy using an LLM the same way the author would've. This actually saves a loss/noise step as the consumers won't need to deploy an llm to summarize the authors llm expanded output.

$ chatgpt make this comment more glib

This is explicitly the problem people notice with LLMs. The text they produce sounds fine only if you are so ignorant of the subject that you can’t properly read it yourself. That’s not a “boon” it’s a flaw.

Reply on news.ycombinator.com