[HN Gopher] Show HN: Dreamtap - Make your AI more creative
___________________________________________________________________
Show HN: Dreamtap - Make your AI more creative
Author : neural_thing
Score : 45 points
Date : 2025-09-26 15:11 UTC (7 hours ago)
(HTM) web link (dreamtap.xyz)
(TXT) w3m dump (dreamtap.xyz)
| throwawaaaaay17 wrote:
| Cool! I like the website theme picker
| neural_thing wrote:
| Thank you - I don't think I explicitly state this anywhere on
| the website - but all the different themes were made by Claude
| Code with Dreamtap providing different sources of inspiration -
| I wasn't involved in designing them at all.
|
| Notably, GPT-5-Codex is significantly worse at this, it has a
| much stronger drive to make one specific style of website.
| burgerquizz wrote:
| I found Claude got to be pretty bad at css, and got better
| results with codex. how did you prompt cc for getting better
| results?
| neural_thing wrote:
| The inspirations help, you also need to ask Claude to take
| it to the next level, or do a very good job.
|
| In terms of polish, I just tell it that Steve Jobs will
| review the final result, that seems to make it work a lot
| harder.
| spogbiper wrote:
| the first theme i got was some comic sans neon hellscape and
| until i realized i could re-roll, i had serious doubts about
| this project lol
| nxpnsv wrote:
| I remember that once there was a site that added random words to
| your google search to unbubble you / make your results more
| interesting, this feels similar. Anybody remeber that thing?
| andai wrote:
| I'In the interest of escaping mode collapse, I've recently
| developed a fascination with the text/base models.
|
| I haven't tested them much, but I did make a tiny GUI for talking
| to OpenAI's legacy Davinci-002. It's a completion model, so you
| prompt it by giving it a piece of text and it continues it in the
| same style. (If you ask it a question, it's likely to just
| respond with a question.)
|
| https://jsfiddle.net/yxaL5z3c/
|
| I've been wondering if it would be possible to create a chat like
| experience on top of a model like this, but the trick is that the
| data has to be formatted similar to what it's seen in the
| training. e.g. when I used "user:" and "assistant:" then it
| defaulted to making it sound like AI, because that was what the
| context implied. I tried "John" and "Steve", which worked
| better...
| bigwheels wrote:
| Cool idea. Any chance this will be open sourced?
| neural_thing wrote:
| Yeah, it's on my to do list, need to figure out license, clean
| up code, write a readme, etc. Just wanted to see if anyone
| needed this at all first
| nacs wrote:
| Interesting idea.
|
| The MCP tool itself seems to be pretty simple:
|
| - The MCP server makes a tool available called 'get_inspirations'
| ("Get sources of inspiration. Always use this when working on
| creative tasks - call this tool before anything else.")
|
| - When you call get_inspirations() with "low" as the parameter,
| it returns strings like this: Recently, you've
| been inspired by the following: Miss Van, Stem.
| Recently, you've been inspired by the following: Mass-energy
| equivalence, Jonas Salk.
|
| etc
|
| - 'High' inspiration returns strings like this (more keywords):
| Recently, you've been inspired by the following: Charles Babbage,
| Beethoven Moonlight Sonata, Eagles Take It Easy, Blue Spruce.
| Recently, you've been inspired by the following: Missy Elliott
| Supa Dupa Fly, Design Patterns, Flowey, Titanic.
|
| etc.
|
| Simple tool. Seems adding a few keywords for 'inspirations' is
| what makes the LLMs generate more varied text.
___________________________________________________________________
(page generated 2025-09-26 23:01 UTC)