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

41–50 of 91 posts

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

#41

Post by mmargenot »

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…

A key part of maintaining a second brain is revisiting and pruning it. Much like a todo list, without that practice it absolutely just accumulates bunk.

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

#42

Post by ModernMech »

hdhdhsjsbdh wrote: post #28
a2ff6eeb0 wrote: post #24

Earlier quoted context omitted.

That's for you to find out. When we automated muscles in the industrial revolution, people used to value strength. Today they value thought. They may value something else in the future.

Seems like the only thing left to value will be social capital. If all forms of labor are free, the only thing that matters is how many people you know, what they think of you, whether they listen to you.

The ultimate goal of project capitalism is to make ownership the only thing in the world that’s valued or valuable. The only thing that matters is how much and who you own.

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

#43

Post by rendaw »

mrtesthah wrote: post #6
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.

Probably good to establish canonical spec documents up front that it can use and maintain as an independent reference?

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.

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

#44

Post by pragma_x »

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 ?

> Could anyone enlighten me as to why to use Obsidian in one's daily life ?

My handwriting has degraded from consistent keyboard use over the last 30 years. Obisidan has replaced my paper notebooks, mostly because of this. However, it is handy to be able to mesh those notes with hyperlinks, LLM output snippets, quotes from other sources, embedded images, etc. Doing all of those other things would be laborious to impossible with paper.

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

#45

Post by parineum »

ModernMech wrote: post #42
hdhdhsjsbdh wrote: post #28

Earlier quoted context omitted.

Seems like the only thing left to value will be social capital. If all forms of labor are free, the only thing that matters is how many people you know, what they think of you, whether they listen to you.

The ultimate goal of project capitalism is to make ownership the only thing in the world that’s valued or valuable. The only thing that matters is how much and who you own.

The actual goal of capitalism is the direct the impulses of the capitalist to align with the interests of the public.

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

#46

Post by post-it »

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 been whittling my way towards having Claude write zero comments in code. They're pretty much never helpful.

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

#47

Post by pc86 »

rendaw wrote: post #43
mrtesthah wrote: post #6

Earlier quoted context omitted.

Probably good to establish canonical spec documents up front that it can use and maintain as an independent reference?

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.

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

#48

Post by avgDev »

rootsudo wrote: post #35

For me it’s the opposite, AI has helped me do the final 20% that I could never do, making execution more painless and more successful.

I've found it very helpful with flushing out bugs, reviewing my code. I have a hard time trusting it to generate 100+ lines of code because in the end I am responsible for it.

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

#49

Post by sdeframond »

post-it wrote: post #46
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 been whittling my way towards having Claude write zero comments in code. They're pretty much never helpful.

How do you do it?

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

#50

Post by theossuary »

a2ff6eeb0 wrote: post #24
gdulli wrote: post #10

What am I even here for if not to have my own ideas?

That's for you to find out. When we automated muscles in the industrial revolution, people used to value strength. Today they value thought. They may value something else in the future.

We didn't automate muscles generally, only specifically. The leverage those specific situations have is so high it's worth it. Same with thinking, it's very far from automated generally. Maybe one day we'll have humanoid robots as generally physically capable, and AI as generally mentally capable, but that's a long way off. Until then there's still emmense value for humans in between the high-leverage areas, and even more value in adding some leverage throughout (like the first attempts at exoskeletons, or using Claude to help manage your daily tasks, etc.)
Post reply on HN