Chonky
AI
text chunking model
SHOW HN2025
How HN took it
2 positive, 1 neutral or asking, 0 mixed, 2 critical, out of 5 comments about the project. Thread score -0.07.
Idea: 1 for, 1 againstDocs: 1 for, 0 againstPerformance: 0 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
Interesting approach; useful for unstructured text from speech-to-text
From 1 comment
This is interesting! I once trained a t5 model by removing newlines from Wikipedia text and it worked surprisingly well / at the time the context length was the biggest issue.…
kamranjon on HN
Documentation and evaluation comparison against rules-based chunking are useful
From 1 comment
you can read the labels this (-y) uses modernBERT and even has an eval comparison to the (-ie) in it's GitHub so you can see the improvement as tested -- although if you want to…
jimmySixDOF on HN
Objections
Example output looks not useful
From 1 comment
That example looks terribly useless. Maybe there's an actually useful application you had in mind? I don't know say Chonk("Hey I forgot my password, this is Tom from X Company")…
TZubiri on HN
Splits related texts and keeps unrelated ones together in the demo
From 1 comment
This is absolutely useless. Tried a few examples yesterday using hf demo. Fcking retarded af. It literally splitted the text in-between of related texts while at the same time…
freakynit on HN
Requests
Show a practical application for the splitting
From 1 comment
That example looks terribly useless. Maybe there's an actually useful application you had in mind? I don't know say Chonk("Hey I forgot my password, this is Tom from X Company")…
TZubiri on HN
Questions
How does it compare to Chonkie's semantic chunking approach
From 1 comment
Took me a minute to realize this is not about Chonkie. I would be interested in how this compares to the other's semantic chunking approach
CjHuber on HN
Alternatives named
Chonkie semantic chunking
From 1 comment
Took me a minute to realize this is not about Chonkie. I would be interested in how this compares to the other's semantic chunking approach
CjHuber on HN
Rules-based chunking
From 1 comment
you can read the labels this (-y) uses modernBERT and even has an eval comparison to the (-ie) in it's GitHub so you can see the improvement as tested -- although if you want to…
jimmySixDOF on HN