Show HN: I wrote a program that hashes files into poems
A new program called rhymesum hashes files into poems using LLM technology. It generates a five-line poem as a unique fingerprint for each file, offering a creative alternative to traditional checksums. The project is intended for fun and is not suitable for production use due to its lack of cryptographic safety.
- ▪Rhymesum uses LLM-generated poems to fingerprint files instead of traditional checksums.
- ▪The program computes a BLAKE3 hash and injects entropy into the LLM sampler.
- ▪It is a toy project and not recommended for production use.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/alebeck/rhymesum |
| Publication time | Sat, 30 May 2026 10:05:16 +0000 |
| Retrieval time | 2026-05-30T10:12:09.050Z |
| Last seen | 2026-05-30T10:12:09.050Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | kVqJtfphblea |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
rhymesum -- Hash files into LLM-generated poems locally Note: This is a toy project and far from cryptographically safe, better don't use it in production. What is this? This project lets you fingerprint your files using LLM-generated poems instead of hard-to-remember checksums. It computes a BLAKE3 hash of the passed file, and based on that injects entropy in both the LLM sampler as well as the prompt itself. The output is a five-line poem representing a fingerprint of your file.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.