Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

It’s so hard to finish an idea that is not yours and is just suggested by AI

ssp.sh

Post reply on HN
Print view View original

131–139 of 139 posts

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#131

Post by t-writescode »

synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on.

I guess my thought / question is: this is your code. Why are you submitting the code to the git repo like that, with all the wrong text? I get making mistakes here or there; but ... everywhere? Enough that it's causing huge problems you can't quickly correct?

And ... aren't you lucky you still *have* the context in your mind? What if you hadn't caught it, or someone else had done that and you inherited that code with those wrong comments that you let through the PR and into the main branch?

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#132

Post by jhartikainen »

tristor wrote: post #95
jhartikainen wrote: post #73

Earlier quoted context omitted.

There seems to be two schools of thought for "second brain" stuff: 1. Those who kind of semi-obsessively write down every little thought, semi-obsessively catalogue everything, etc. 2. Those who use the idea of "writing helps you think", where the second brain functions in support of this Personally I find 2 quite valuable, and although I could "think about programming all the time" (or one of my other interests), I…

Writing does help you think... but only if you write. Dumping a bunch of stuff into a "second brain" is not you writing. Keeping a journal is you writing. Those serve similar functions, but keeping a journal is more intentional and requires you to think critically about your inputs and decide what to record and how, which is the thinking part that comes with writing. That summarization that LLMs are doing for people…

100%. The term "second brain" is getting kind of a bad rep because of people using the dump+AI method. I don't think Tiago Forte who, as far as I know, coined the term meant doing that, at least based on his book on the subject.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#134

Post by debugnik »

preommr wrote: post #76
synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

I've had codex delete useful (albeit not directly relevant or perhaps messy wip notes) comments, even though I explicitly have it in my agents.md not to delete comments, and ask for permission if it thinks it should. It deleted the comments, and when I asked why it did that even though I expressedly asked it not to, it responded that me prompting it in the first place explicit permission. I have no idea if that's the…

> and when I asked why it did that even though I expressedly asked it not to

Just be clear, it can't know, and by asking you're just making it roleplay as someone excusing themselves.

It's very unlikely that the choice to remove the comment was driven by an internal monologue based on learned criteria that it can refer to. The sampler most likely picked tokens to remove it while writing the patch, because that's what the statistics modelled, and that's it.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#135

Post by bojan »

t-writescode wrote: post #131
synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I guess my thought / question is: this is your code.…

> Why are you submitting the code to the git repo like that, with all the wrong text?

According to my enterprise architect I shouldn't be reviewing code, it's a waste of time in this new reality.

I'm still doing it because it's going to be me answering that 3 AM call. But I don't know for how long I'll be allowed to swim upstream like that.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#136

Post by oblio »

gmueckl wrote: post #129
oblio wrote: post #127

Earlier quoted context omitted.

Most lint tools allow exceptions if you add a special marker. I think even allow custom user exceptions. E999: human generated comment :-)

But then the LLMs sees the syntax and is likely able to mimic it.

Shouldn't the "human generated comment" part be a strong hint not to?

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#137

Post by fsnovask »

Dependance wrote: post #32

Could anyone enlighten me as to why to use Obsidian in one's daily life ? I have a dozen ideas popping a day and nothing comes close in terms of ease than a paper notebook for capturing and some apple notes equivalent for storage. Used to have a Notion but all the "Second Brain" movement seems...fishy to me ?

There's also an article from this same site about that: https://www.ssp.sh/brain/digital-vs-paper

IMO it's way better to do what you think is good, whether that's Obsidian, notebooks, or something else

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#138

Post by ThunderSizzle »

bartread wrote: post #62
synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

Delete the comments: I’ve gone on a tear with these recently because they’re nothing but trouble. The absolute least worst outcome is they chew up your token budget. But what tends to happen, and this is much more serious, is they poison future work and make further modification of the codebase more burdensome and error prone.

I use comments for external domain constraints (e.g. this table has three types of records in them that we use for different purposes - I might have the LLM agent be a bit thorough and clearer with the explanation, but I found those type of comments very much helped future iterations)

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#139

Post by qsera »

bojan wrote: post #135
t-writescode wrote: post #131

Earlier quoted context omitted.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I guess my thought / question is: this is your code.…

> Why are you submitting the code to the git repo like that, with all the wrong text? According to my enterprise architect I shouldn't be reviewing code, it's a waste of time in this new reality. I'm still doing it because it's going to be me answering that 3 AM call. But I don't know for how long I'll be allowed to swim upstream like that.

I have found manual reviewing of LLM generated code to be an uphill battle. LLMs does not believe in abstraction. So complexity spills everywhere. Some details in the lowest level might be handled separately in more than one place, at the higher levels. In a short while it is a copiously documented unreadable mess (both code and documentation).

LLM written PR descriptions and comments are a sight to behold. I am not sure how stuff can be written so cryptically. It seems that LLMs just make up what ever terminology so that it can cram as much details into a single sentence as possible! I generally just paste it to chatgpt and ask it to decrypt it.

Post reply on HN