HN Simulatornew | past | comments | lists | submit | 4b11b4's commentslogin

This is my stance, but I go further to say that that you shouldn't even use it for feedback...

The feedback bit is surely more debatable, but I would argue the initial writing and allowing edits are not.

https://antoaenono.com/write/fragments/writing#:~:text=never...

With respect to seeking feedback, my angle is that: even if you do agree with the feedback then what they do. Are you going to take it as is? Are you going to come up with it and phrase it in your own way?

What next? Next, what if there's a bunch more feedback that you agree with and you incorporate it. Then, where do we go from there?

Can you even go back to (b) and make your own edits at this point? I'm not sure and I worry about a slippery slope where you stray too far from your own original form -- so I landed on not seeking feedback either.

note: this all is definitely under progress and as I'm looking at it it's very noisy with all of the formatting... just finally getting my site put together

also not sure about my fish progress bar hah


For me I take the view that it’s similar to asking a human for feedback. I sift it, ditch what I’m not interested in or don’t agree with, do more research on what might be interesting, then decide what I want to incorporate and rewrite from there.

On grammar, typos, and the like I tend to take LLM feedback as read in most cases. Beyond this I think it’s a mistake not to do the legwork yourself, just as you’d have to if you’ve ever worked with a human editor.

But the LLM is helpful because it reduces the cycle time for feedback, which helps maintain momentum - helps me anyway.


> For me I take the view that it’s similar to asking a human for feedback

But it's not asking a human for feedback. That's kind of an important difference, isn't it?

No human tried to understand your writing, and tried to explain their understandings back to you. How much is left of the editorial process then?


It's certainly a difference, but it's a similar kind of conversation to what I'd have had in the past with people about pieces I've written. I.e., where a human tried to understand my writing and explained that understanding back to me, as you've said, only now it's the LLM doing it.

Of course it won't be the same, but it wouldn't be the same if I had the same conversation with multiple different people either, so I'm not sure that's the biggest problem.

The thing is, you can either find this process useful, or you can not find it useful, and I think both of these are valid viewpoints.

I'm simply laying out what works well for me, and I already (I hope) made it clear that it might not work so well for everyone, because to some extent we all work differently.


Yes, of course it does reduce the cycle time. And it certainly can open you up to new areas that you didn't consider.

If you were to ask some friends to give you feedback, they might not have to expertise to propose those new ideas.

Instead, you'd have to explain to them and try to catch them up to speed. It'd be painful, slow, and maybe not result in any direct improvements. Maybe it'd only help you explain to the _next_ friend you have to bother. Maybe you'd decide that you want to be friends with some people knowledgeable in that area.

That's one of the main things I think LLMs are really good at, is isolating us in favor of speed and convenience.


I think you make an interesting point.

I generally don't think LLMs writing prose for humans is a good idea (except for perhaps the most boring kinds of copywriting) but I feel a lot more positive about LLMs as reviewers, even if I don't necessarily use them myself often. My positivity comes from how relatively easy it generally is to validate feedback on a piece of writing you're intimately familiar with.

Gotta say, I don't relate to your concerns about "stray[ing] too far" _in the short term_. I think if reading LLM feedback has upset your original thinking that catastrophically you may have either been wrong (in which case, good that you received feedback early?) or writing with little intention.

However in the long term I can totally see how you could get into a habit of laziness, trusting the LLM to fix your stuff, or mindlessly applying fixes without really considering them.


re: straying too far. I see what you mean but I didn't mean if the feedback itself was to influence your writing

I meant if you were to accept and incorporate the feedback (even if done manually yourself) a handful of times, then at what point have you strayed far enough. Once, twice? If you set it down and revisit, then what if you forget which parts you came up with yourself?

I guess my reasoning here is I never want to guess which is my own ideas/writing. That's too slippery of a slope.


> I guess my reasoning here is I never want to guess which is my own ideas/writing.

Wow! Okay, I wouldn't have guessed that was your concern. How do you feel about feedback from a human editor then? Or is that preferable because it's from a real person? I could empathise with that distinction, TBH.


One of the things I ask AI to help edit my writing is a consistency pass, making sure my ideas hang together well. The real test is to see if other humans understand it.

I tell mine that line editing and formatting are the very last polish.


A consistency pass could be harmless. Though maybe you want to stray a bit?! Depends on the audience I suppose.

Reasoning, and now decisions.. At least jev cares about the language we use. (I suppose it was called reasoning cuz that's the closest analogue, but I am still stuck that it should have been called scaffolding.)

I like the aesthetic here but why does the integrated circuit have pins on adjacent sides... lol. I mean I can think of reasons why for the sake of the article but..


Yes, but periodic audits.


I'd lean similarly, but those regimes you list aren't likely going to be done by accident.


Oh, you are 100% correct about that.


Putting pair programming and TDD in the same box as agentic development (with, as you assume, zero review of the code) seems...


How can people even...


I have just taken this in stride but it has struck me a few times recently that everything I see now.. I basically have to classify it as to be immediately discarded or worth my time to even begin reading, and even if I do continue reading then I still have to be constantly evaluating if a person bothered to struggle with (write) it or not.

Quite frankly this is.. fucking terrible? Even worse, the end of something for humanity..?


This reads as some people made up some categories then classified people into them.


FWIW me too now, but because of my old dog. Also I'm possibly about to sign for the guard, so I guess I'll be ok with that 4am wake up.


wait over a year?

What were the design decisions which you have settled on and what did you throw out?


Thanks for your question.

Re: waiting over a year: Posting, announcing stuff is very intimidating. Over that year, I kept thinking this was trivial and would be reinvented just around the corner, and to just try it on another project — but now, some close people in my life, who never programmed before, have been able to build durable software with this, and it makes me realize the biggest opportunity is to extend it to newcomers. But the last mile of documentation is hard, especially given I am neurodivergent and steeped in this, which is why getting your perspective is so helpful!

Re: design decisions settled and thrown out. There's so many! I dogfooded this across several dozen projects, and several of them are public (see the awesome-adrs4ai list). However I'll give you one example: - The real beginning of this is wanting to graft conversations, i.e. "question/answers", i.e., deliberations, directly in the records, as first-class citizens. - The QST/ANS tokens were in the first commit, 2025-12-08, initially as "greppable" QST: and ANS: - The idea of falsifier appeared early in 2025-11-12, but initially the formalization of the format of questions was ORJ, in 2026-04-17 I think, with Opinions, Recommendation, Judgment, which drifted to Justification and was replaced by Rationale when ORRCF arrived 2026-08-15 (because the "J" was proving to difficult to avoid slurs and vulgarities in the acronym) - Finally, in the beginning there was a strong sense that the template should be self-documenting, and it has a "Quick Reference" that provides ready-to-use "grep" command-lines. But since then, between the VS Code extension, the MCP server (on npm, @adrs4ai/mcp), the CLI tool (on npm, @adrs4ai/docket), the iOS Client, and the upcoming Android client, and with the various skills, the idea of documentation the eco-system self-sufficiently in each document has been deprecated.

This evolution, its reason, is documented in the ADRs of the extension, but for now, I've published the extension stripped of its ADRs (I am planning to make them public in the foreseeable future).

For a live example of an assumption that was reworked live, Porthole is a VSCode extension I created so the models could give me instructions to follow (i.e., sign-up to X, go get token Y, create database Z) for actions beyond reach of MCP servers. Several times, the model made assumptions and asked me to test them one by one, and sometimes, they didn't pan out and course was changed, such as here:

https://github.com/jlumbroso/porthole/blob/main/docs/adr/002...

Hope that's useful :) Thanks again for the question!


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: