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

111–120 of 123 posts

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

#111

Post by selcuka »

pc86 wrote: post #47
rendaw wrote: post #43

Earlier quoted context omitted.

That doesn't solve the problem of it hallucinating more design details and putting them in comments. The solution to too much authoritative documentation isn't more authoritative documentation.

Comments exist for humans to understand the why of the code, including perhaps external dependencies/assumptions/requirements. LLMs inserting code comments makes zero sense by definition.

> LLMs inserting code comments makes zero sense by definition.

Not completely, because anyone who reviews the code in the future does not have access to your original prompt, so theoretically leaving a comment that explains the "why" portion of the prompt would be useful. LLMs rarely do that, though.

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

#112

Post by hadlock »

mccoyb wrote: post #31

I don't get the second brain thing. I don't keep a second brain, I just read and think a lot. I once did a physics masters and, when asked how to make steady progress, one of the professors (who had published with Paul Dirac no less) made the comment "well, my secret is that I think about physics all the time" I started practicing this for the stuff I'm interested in ... and the result is that I generate a lot of ide…

>I don't get the second brain thing. I don't keep a second brain, I just read and think a lot.

Yes, but writing also helps you lens your thoughts in a completely different way. This is why so many people journal, or blog, or vlog, even though only a handful of people might actually audit their output. Obsidian sort of abdicates a lot of the value of journaling, but I think there's still some (although much less, perhaps 5% as much) value in the actual act of directing the journaling, even if the rest of the thinking is outsourced to the clanker.

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

#113

Post by chadcmulligan »

zahlman wrote: post #109
chadcmulligan wrote: post #103

what happened to ideas are cheap - execution is everything. As Claude said to me when I said the same thing - it's not really its idea you had to ask the right questions. I find this true in some ways - asking the right question and finding out what the AI's have hidden inside them is like panning for gold imho.

> what happened to ideas are cheap - execution is everything. It used to be that we only recognized a tiny fraction of the actual ideas involved, because most of them were intermingled with execution. We would sit there and bang out code at single-digit WPM while trying to keep block diagrams of process memory (or UML diagrams, or whatever else) in our heads, and then run the compiler and/or the tests and realize we'…

I never really bought into it, I still think ideas are hard, and execution may be a little easier, but still hard to. The lack of thousands of amazing new startups since AI sort of validates this.

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

#114

Post by trenchgun »

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.

Why delete comments! Constrained grammar! Make invalid state unrepresentable.

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

#115

Post by wafflemaker »

recursive wrote: post #86
preommr wrote: post #76

Earlier quoted context omitted.

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…

There might not be an "actual" reason that's expressible in human-comprehensible language.

Moreover, even if there was a reason, it was there "in the model" at the moment of generation.

The new model can only guess/hallucinate when ordered to give reasons.

It's like having an actor play a role while wearing a hat. Then the next actor comes, puts on the same hat, and we're asking them to explain why "they" did something while there was someone else playing the role.

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

#116

Post by Utilera »

AI is great as a query layer over my notes, but I don't really want it contributing to them. The whole value of old notes is that they preserve what I noticed at the time. If half the vault becomes competent-sounding generated text, searching it five years later seems much less useful...

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

#117

Post by Utilera »

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.

This is almost worse in code because the hallucination starts looking like documentation

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

#118

Post by hombre_fatal »

pc86 wrote: post #47
rendaw wrote: post #43

Earlier quoted context omitted.

That doesn't solve the problem of it hallucinating more design details and putting them in comments. The solution to too much authoritative documentation isn't more authoritative documentation.

Comments exist for humans to understand the why of the code, including perhaps external dependencies/assumptions/requirements. LLMs inserting code comments makes zero sense by definition.

LLMs benefit from knowing the why, the intent, and the reason/justification for code to exist, too.

Catching code desyncing from it is a valuable place to reconsider assumptions and maybe even invariants.

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

#119

Post by luxshan_t »

In research, we can use AI efficiently to identify gaps and then validate them, but the final idea should be our own. I’ve faced an issue where, when AI suggests something unfamiliar, the research may not become successful because we start relying on it too much. Instead of actually learning and doing research, we become good prompters, and our brains start thinking, "How should I ask Claude to do this?" rather than thinking deeply about the research problem itself.
Post reply on HN