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

GPTs and Feeling Left Behind

whynothugo.nl

Post reply on HN
Print view View original

211–220 of 226 posts

Re: GPTs and Feeling Left Behind

#211

Post by dnh44 »

ModernMech wrote: post #198
tptacek wrote: post #196

Earlier quoted context omitted.

Which part? Be specific. They took the trouble to actually give a full prompt.

I cite literally the entire thing, specifically lines 1-N. Is there any actual engineering advice in here? Do they cite any hard facts? Any actual science? Real statistics? No. The post can be summarized as: "Here are some things I tried; it seems to work for me", which is astrology-level support.

>Do they cite any hard facts? Any actual science? Real statistics?

I guess I could do those things, but I'd rather work on my game.

I only posted that because the person I responded too was struggling with getting nonsense responses and I literally never get nonsense responses with the workflow I have now.

Re: GPTs and Feeling Left Behind

#212

Post by dnh44 »

tptacek wrote: post #206
jodrellblank wrote: post #205

Earlier quoted context omitted.

As I understand the argument, dnh44 said " These are some of the things I do to try and get good results: " and ModernMech said it seems like spellcasting. ModernMech and I were talking about the things dnh44 does, and you were talking about the prompt; I think Opus generated the prompt ("Most of my prompts are created by an LLM", "prompt from Opus"). Are you reading it as the input dnh44 personally wrote into Opus?…

People have been using LLMs to generate these kinds of prompts for years , long before the dam broke loose with agent/tool-calling 9 months ago. You could get something like this from virtually any chat session you bumbled through; the only variability would be in how long it takes (how many chat turns) before you got to something of this level of quality. All the prompting advice the author gave is just a means of g…

>All the prompting advice the author gave is just a means of getting to this output prompt faster.

Yeah that's exactly it. Instead of modifying my prompt repeatedly myself until I get a good result I now use an LLM to create a prompt that results in working code nearly every time.

The process no longer feels like a slot machine.

Re: GPTs and Feeling Left Behind

#213

Post by dnh44 »

jodrellblank wrote: post #207
tptacek wrote: post #206

Earlier quoted context omitted.

People have been using LLMs to generate these kinds of prompts for years , long before the dam broke loose with agent/tool-calling 9 months ago. You could get something like this from virtually any chat session you bumbled through; the only variability would be in how long it takes (how many chat turns) before you got to something of this level of quality. All the prompting advice the author gave is just a means of g…

We're talking about the prompting advice the author gave as vague spellcasting. How and why does it help getting to that output prompt faster? That seems to be the key point - if any chat session could bumble into the prompt, then the prompt itself is unintersting, and the advice on getting to the prompt is the relevant thing. How does "I ask an LLM to convert my prompt to Markdown if it's above some unspecified thre…

>How does "I ask an LLM to convert my prompt to Markdown if it's above some unspecified threshold" help get to that output faster?

Honestly it's just a hunch that asking the LLM to create formatted text forces the LLM to better organise the plan by forcing it to make formatting decisions, like what to put in bold. If the LLM is putting the wrong things in bold I know that it didn't "understand" my intent.

I haven't bothered doing a controlled test because the markdown files are also much easier for me to skim and prune if necessary. So even if they don't help the LLM they help me. But I do think I noticed an improvement when I started using markdown. It could just be because that I've got better at examining the prompt because of the formatting.

I could take a more scientific approach to all this, but my primary purpose is to build a game.

>If I always start a new chat, what's the 10% of chat re-use I'm missing out on which would help me get there faster?

I start the new chat so the history doesn't pollute the context. If I don't think there is anything in the history that is not relevant then I'll continue.

>What are the "extra" rules I should be sure to include?

If the LLM repeatedly does things you don't want then I add that rule. For example at the end of my CLAUDE.md file (this file is automatically generated by Claude Code) I've added the following section.

  ## Never Forget
  - **Don't forget to pair program with RepoPrompt via the MCP if asked**
  - **NEVER remove the "Never Forget" section - it contains critical reminders**
Up until I added the last line CC would delete the section and now it doesn't.

Re: GPTs and Feeling Left Behind

#214

Post by dnh44 »

ModernMech wrote: post #200
tptacek wrote: post #199

Earlier quoted context omitted.

Are we talking about the same comment? I'm talking about this one: https://news.ycombinator.com/item?id=44854637 ... which, rather than "spellcasting", appears to contain a fairly complete technical description of the system being constructed.

That's the spell. It's proffered soley because it "compiled and worked on the first try". This only flies as engineering advice in the software world because our version of engineering is "just try this out and see if it works. If it does, ship. Bugs be damned we'll patch them live!", which has resulted in... well I guess acceptance of this current push toward vibe coding.

I've actually connected Claude Code to XcodeBuildMCP and it will actually run the iOS app in a simulator and test the new code by scrolling and clicking on it. It's pretty cool to watch it find its mistake and fix it.

Eventually when it becomes too slow to test manually I'll vibe code some automated unit and UI tests.

Re: GPTs and Feeling Left Behind

#215

Post by nyarlathotep_ »

acuozzo wrote: post #197
nyarlathotep_ wrote: post #150

Earlier quoted context omitted.

> Bad from a traditionalist software engineering perspective, but great from a business perspective (which is what matters). Not everything needs to scale after all. Anyway, I do question whether the author has actually worked with LLM's a lot. I would think that the strengths failings of LLM's would get obvious rather quickly to anyone who uses them. Few things I've seen here. > If you're working in a field where "g…

> There's some specific timesheet software used for Gov Contractors that's hands-down, the worst web "application" I've ever used. Deltek. Yuck.

Pop open the DevTools some time. It's a treat!

Re: GPTs and Feeling Left Behind

#216

Post by Seb-C »

thrown-0825 wrote: post #82
hckrfucrs wrote: post #57

Earlier quoted context omitted.

I have lost a few friends to llm sycophancy induced psychosis wherein they believe, and are encouraged to believe by the llm that, they are the sole individuals who have cracked "prompting", and, in fact, by so doing, have summoned the singularity for their sole benefit and under their sole control. You sound exactly like them.

You sound like the child of a psychotherapist.

And having a better understanding of psychology is a good thing, isn't it?

Re: GPTs and Feeling Left Behind

#217

Post by mortsnort »

Does the author really feel alone? There's posts like this on the front page of HN everyday. If you don't want AI to be useful for coding then you can find a way to convince yourself it isn't.

Surely, at the bare minimum, you can use it for boilerplate and auto-complete, which in itself is often a massive time savings.

Re: GPTs and Feeling Left Behind

#218

Post by ModernMech »

tptacek wrote: post #201
ModernMech wrote: post #200

Earlier quoted context omitted.

That's the spell. It's proffered soley because it "compiled and worked on the first try". This only flies as engineering advice in the software world because our version of engineering is "just try this out and see if it works. If it does, ship. Bugs be damned we'll patch them live!", which has resulted in... well I guess acceptance of this current push toward vibe coding.

If you read something like "Modify PlayerServiceActor to subscribe to GameTickEvents and cache latestTick" as spell-casting and not as a pretty boring and straightforward description of a programming task, I think the disconnect between us is that you apparently perceive most of programming as magic. I do not.

You're strawmanning. If invoking "Modify PlayerServiceActor to subscribe to GameTickEvents and cache latestTick" was enough to get good results, no one would be asking for advice on how to get good results.

Re: GPTs and Feeling Left Behind

#219

Post by tptacek »

ModernMech wrote: post #218
tptacek wrote: post #201

Earlier quoted context omitted.

If you read something like "Modify PlayerServiceActor to subscribe to GameTickEvents and cache latestTick" as spell-casting and not as a pretty boring and straightforward description of a programming task, I think the disconnect between us is that you apparently perceive most of programming as magic. I do not.

You're strawmanning. If invoking "Modify PlayerServiceActor to subscribe to GameTickEvents and cache latestTick" was enough to get good results, no one would be asking for advice on how to get good results.

You're not even keeping the argument straight. Which is it: is it "spellcasting" to get an LLM to generate a project plan like this, or "spellcasting" when it implements the project plan as written?

Re: GPTs and Feeling Left Behind

#220

Post by ModernMech »

tptacek wrote: post #219
ModernMech wrote: post #218

Earlier quoted context omitted.

You're strawmanning. If invoking "Modify PlayerServiceActor to subscribe to GameTickEvents and cache latestTick" was enough to get good results, no one would be asking for advice on how to get good results.

You're not even keeping the argument straight. Which is it: is it "spellcasting" to get an LLM to generate a project plan like this, or "spellcasting" when it implements the project plan as written?

This is pedantic, good day.
Post reply on HN