Penny-1.7B
AI
style transfer language model
SHOW HN2025
How HN took it
4 positive, 9 neutral or asking, 0 mixed, 5 critical, out of 18 comments about the project. Thread score +0.02.
Execution: 0 for, 4 againstIdea: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Whimsical and fun project
From 3 comments
what a wonderful work of whimsy! well wrought. I'd love to have a library of these, so I could pipe text into `penny`, `brainrot`, `pony`, `newspeak`, `corporate`, `scp`, `trek`…
sterlind on HNthis is awesome
fitsumbelay on HNLove it. Immediately reminded of the text filters back in the day like the pirate one that would drop letters and replace with apostrophes and change certain passages into "arr"…
npunt on HN
Idea of a library of text style filters
From 1 comment
what a wonderful work of whimsy! well wrought. I'd love to have a library of these, so I could pipe text into `penny`, `brainrot`, `pony`, `newspeak`, `corporate`, `scp`, `trek`…
sterlind on HN
Objections
Output uses modern LLM-style words like delve
From 2 comments
Nice work ! It still manage to use the word 'delve' in the first sentence, which is a giveaway that it's written by a LLM.
ekianjo on HNIts considered an LLM tell because its a term that is rarely used by the median modern casual writer; its not at all uncommon even in current literature [0], and its even more…
dragonwriter on HN
Example contains a historical error about Napoleon
From 1 comment
Kinda of strange to pick an example that is just wrong. It's supposed to be written from 1840 and says Paris is the seat of Napoleon almost 20 years after he died.
_1 on HN
Output is more complex than the source journals
From 1 comment
I'm not sure if you've tried this already, but removing the translate step might give you a more authentic output. In the journals that I saw, the language was much more simple…
KaiserPro on HN
Repeated adjectives in adjacent sentences
From 1 comment
The repetition of adjectives in adjacent sentences is much more of a tell than using the word delve, imo.
rndmio on HN
Requests
Publish training code or notebook
From 3 comments
what a wonderful work of whimsy! well wrought. I'd love to have a library of these, so I could pipe text into `penny`, `brainrot`, `pony`, `newspeak`, `corporate`, `scp`, `trek`…
sterlind on HNThis is really cool! Do you have any of the pipeline code available that you used for training? I am curious about how you created the reward model. I love little projects like…
kamranjon on HNHave you written anywhere in detail on how you gathered your dataset and trained the finetune? I have a few use cases that are like this, but I'm not sure where to start.
veggieroll on HN
Remove the translate step for more authentic output
From 1 comment
I'm not sure if you've tried this already, but removing the translate step might give you a more authentic output. In the journals that I saw, the language was much more simple…
KaiserPro on HN
Add a penalty for LLM giveaway words
From 1 comment
Haha! You’re right. Maybe I’ll add a penalty for that and some other giveaway words and make a revision.
deepsquirrelnet on HN
Questions
Why no supervised fine-tuning was used
From 1 comment
You mention no supervised finetuning. May I ask why? I'm curious if you could get similar/better/worse results by just finetuning the LLM on your dataset rather than generating…
throwaway314155 on HN
How the reward model was created
From 1 comment
This is really cool! Do you have any of the pipeline code available that you used for training? I am curious about how you created the reward model. I love little projects like…
kamranjon on HN
Alternatives named
Antislop sampler for suppressing overused words
From 1 comment
This is easily fixed with the antislop sampler. https://github.com/sam-paech/antislop-sampler
Der_Einzige on HN
Pirate and jive text filters
From 2 comments
Love it. Immediately reminded of the text filters back in the day like the pirate one that would drop letters and replace with apostrophes and change certain passages into "arr"…
npunt on HNReminds me of this: https://www.unix.com/man_page/debian/6/jive/
latchkey on HN