Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This is the CRUX of the issue. Even with SOTA models (Sonnet 3.5, etc) - the more open-ended your prompt - the more banal and generic the response. It's GIGO turtles all the way down.

I pointed this out a few weeks ago with respect to why the current state of LLMs will never make great campaign creators in Dungeons and Dragons.

We as humans don't need to be "constrained" - ask any competent writer to sit quietly and come up with a novel story plot and they can just do it.

https://news.ycombinator.com/item?id=43677863

That being said - they can still make AMAZING soundboards.

And if you still need some proof, crank the temperature up to 1.0 and pose the following prompt to ANY LLM:

  Come up with a self-contained single room of a dungeon that involves an 
  unusual puzzle for use with a DND campaign. Be specific in terms of the 
  puzzle, the solution, layout of the dungeon room, etc. It should be totally 
  different from anything that already exists. Be imaginative. 
I guarantee 99% of the returns will return a very formulaic physics-based puzzle response like "The Resonant Hourglass", or "The Mirror of Acoustic Symmetry", etc.


When using Claude Sonnet 3.7 for coding, I often find that constraints I add to the prompt, end up producing unintended side effects.

Some examples:

- "Don't include pointless comments." - The model doesn't keep track of what it's doing as well, I generally just do another pass after it writes the code to simplify things.

- "Keep things simple" - The model cuts corners(often unnecessarily) on things like type safety.

- "Allow exceptions to bubble up" - Claude deletes existing error handling logic. I found that Claude seems to prefer just swallowing errors and adding some logging, instead of fixing the underlying cause of the error, but adding this to the prompt just caused it to remove the error handling that I had added myself.


The unfortunate implication to this is that many codebases Claude has been trained on just choose not to handle errors...


> I guarantee 99% of the returns will return a very formulaic physics-based puzzle response like "The Resonant Hourglass"

Haha, I was suspicious, so I tried this, and I indeed got an hourglass themed puzzle! Though it wasn't physics-based - characters were supposed to share memories to evoke emotions, and different emotions would ring different bells, and then you were supposed to evoke a certain type of story. Honestly, I don't know what the hourglass had to do with it.


Temperature 1.0 results are awful regardless of domain. 0.7 to 0.8 is the sweet spot. No one seems to believe this till they see for themselves.


Out of curiosity, I used your prompt but added "Do not make it a very formulaic physics-based puzzle."

The output is pretty non-sensical: https://pastebin.com/raw/hetAvjSG


It is totally different from anything that exists. It fulfils the prompt, I suppose! It has to be crazy so you can be more certain it's unique. The prompt didn't say anything about it being good.


I liked the puzzle and I think I could DM it.


Hardest part is ‘combining emotions on the mesh’ and all the realizations involved. You can do your own thing with the setup alone though.


Yeah this was the part I found a little silly, mostly because I just couldn't visualize what that mesh looked like or how I would describe how to operate it.


# The Synesthetic Challenge Chamber

## Room Layout

The room is a simple 30-foot square with a single exit door that's currently sealed. In the center sits a large stone cube (roughly 5 feet on each side) covered in various textured surfaces - some rough like sandpaper, others smooth as glass, some with ridged patterns, and others with soft fabric-like textures.

Around the room, six distinct scent emitters are positioned, each releasing a different aroma (pine, cinnamon, ocean breeze, smoke, floral, and citrus). The room is otherwise empty except for a small stone pedestal near the entrance with a simple lever.

## The Puzzle Concept

This puzzle operates on "synesthetic translation" - converting sensory experiences across different senses. The core concept is entirely verbal and tactile, making it fully accessible without visual components.

## How It Works

When players pull the lever, one of the scent emitters activates strongly, filling the room with that particular aroma. Players must then approach the central cube and touch the texture that corresponds to that smell according to a hidden synesthetic logic.

The connection between smells and textures follows this pattern: - Pine scent → ridged texture (like tree bark) - Cinnamon → rough, granular texture (like spice) - Ocean → smooth, undulating surface (like waves) - Smoke → soft, cloudy texture (like mist) - Floral → velvet-like texture (like petals) - Citrus → bumpy, pitted texture (like orange peel)

After correctly matching three smell-texture pairs in sequence, the door unlocks. However, an incorrect match causes the lever to reset and a new random smell to emerge.

## Communication & Accessibility

The DM describes the smells verbally when they're activated and can describe the various textures when players explore the cube by touch. The entire puzzle can be solved through verbal description, touch, and smell without requiring sight.

For extra accessibility, the DM can add: - Distinct sounds that play when each scent is released - Textured surfaces that have subtle temperature differences - Verbal clues discovered through successful matches

## What Makes This Unique

This puzzle uniquely relies on cross-sensory associations that aren't commonly used in dungeons. It: - Doesn't rely on visuals at all - Uses smell as a primary puzzle component (rare in D&D) - Creates unusual connections between different senses - Has no mathematical, musical, or traditional riddle elements - Can be experienced fully regardless of vision status - Creates interesting roleplaying opportunities as players discuss how different scents "feel" texturally

For the DM, it's easy to describe and implement while still being conceptually unique. Players solve it through discussion, exploration, and experimentation rather than recalling common puzzle patterns.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: