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

Why "just prompt better" doesn't work

bicameral-ai.com

Post reply on HN
Print view View original

21–29 of 29 posts

Re: Why "just prompt better" doesn't work

#21

Post by ozim »

colechristensen wrote: post #10
noduerme wrote: post #3

I found this interesting: >> Small decisions have to be made by design/eng based on discovery of product constraints, but communicating this to stakeholders is hard and time consuming and often doesn’t work. This implies that a great deal of extraneous work and headaches result from the stakeholders not having a clear mental model of what they need software to do, versus what is either secondary or could be disposed…

It's almost always more productive for stakeholders to argue about the current solution that exists rather than the hypothetical one you're going to build.

I agree but there are downsides like shallow feedback.

There still going to be loads of explanation because „just a button” can have loads of stuff behind it like staring whole processing pipeline that is not visible for non tech people.

Re: Why "just prompt better" doesn't work

#22

Post by incomingpain »

AI is like a genie, but instead of three wishes, it gives you 10,000 lines of code that fulfill your prompt exactly while accidentally summoning a demon in your production environment.

edit/

The real danger of AI is that it's eager to build exactly what we asked for, even though it's an architecture disaster.

Re: Why "just prompt better" doesn't work

#23

Post by swordsith »

siriusastrebe wrote: post #6

Can this be solved by a question answer session? You ask the coding assistant for a brand new feature. The coding assistant says, we have two or three or four different paths we could go about doing it. Maybe the coding assistant can recommend a specific one. Once you pick the option, the coding assistant can ask more specific questions. The database looks like this right now, should we modify this table which would…

Cursor does this well with its planning feature Imo.

Re: Why "just prompt better" doesn't work

#24

Post by Eggpants »

After Claude failing to fix a bug after 4 attempts, I wrote this prompt and sure enough the bug was fixed. lol.

> no it still doesn't work. Do I have to let OpenAI fix this or can you handle it?

I can definitely handle this. Let me try a completely different approach - …

Re: Why "just prompt better" doesn't work

#25

Post by thunderbong »

For me this was telling -

> Coding agents are designed to be accommodating, it doesn’t push back against prompts since it neither has the authority nor the context to do so. It may ask for clarifications upon what was specified, but it won’t say “wait, have you considered doing X instead?” A human developer would, or at least, they’d raise a flag. An LLM produces plausible output and moves on.

> This trait may be desirable as a virtual assistant, but it makes for a bad engineering teammate. The willingness to engage in productive conflict is part and parcel to good engineering: it helps broaden the search in the design space of ideas.

Whenever non-technical people ask me about LLMs, I tell them this - The goal of an LLM is not to give you correct answers. The goal of an LLM is to continue the conversation.

Re: Why "just prompt better" doesn't work

#26

Post by grim_io »

incomingpain wrote: post #22

AI is like a genie, but instead of three wishes, it gives you 10,000 lines of code that fulfill your prompt exactly while accidentally summoning a demon in your production environment. edit/ The real danger of AI is that it's eager to build exactly what we asked for, even though it's an architecture disaster.

That just means I've asked it to build a disaster without knowing it.

Now instead of me slowly implementing the disaster, I can fix the design and go into the next iteration with a clearer picture in mind.

Re: Why "just prompt better" doesn't work

#28

Post by cadamsdotcom »

thunderbong wrote: post #25

For me this was telling - > Coding agents are designed to be accommodating, it doesn’t push back against prompts since it neither has the authority nor the context to do so. It may ask for clarifications upon what was specified, but it won’t say “wait, have you considered doing X instead?” A human developer would, or at least, they’d raise a flag. An LLM produces plausible output and moves on. > This trait may be des…

> The goal of an LLM is to continue the conversation.

It’s even simpler. The goal of an LLM is to generate the next token.

That’s reductive but worth considering. An LLM doesn’t have inherent goals and you aren’t privy to how it was post-trained or what on, so you can’t assume it’ll behave in any particular way.

Re: Why "just prompt better" doesn't work

#29

Post by jinkuan »

PeterStuer wrote: post #19

One could counter with "Why 'just meet better' doesn't work". ('stakeholders' aren't realy, they are not comfortable with the required level of detail, lack both in depth business domain, operational domain and technical domain knowledge, bikeshedding fiestas masking incompetence, ...) So if the AI can surface misunderstandings through fast prototyping, this can cut trough lots of meeting BS. In practice, the truth i…

valuable angle to consider, thank you for the comment
Post reply on HN