It's a totally different approach, but maybe you're right, good LLMs are relatively ...

2025-02-11 00:22:14

It's a totally different approach, but maybe you're right, good LLMs are relatively new and maybe could be considered to supersede fuzzy hashing. But the main problem of reverse-engineering the compression algorithm (which is one way to think about llms) still exists. If you're thinking of working on this I'm happy to see what I can do to help.

Author Public Key

npub1jlrs53pkdfjnts29kveljul2sm0actt6n8dxrrzqcersttvcuv3qdjynqn

Seen on

wss://nos.lol wss://nostr.mom

Show more details

Published at

2025-02-11 00:22:14

Kind type

1 Short Text Note

Event JSON

{ "id": "2ec22f92696d6463f3dcbc8e889da517e901318866eaba638578d9205868ba80", "pubkey": "97c70a44366a6535c145b333f973ea86dfdc2d7a99da618c40c64705ad98e322", "created_at": 1739233334, "kind": 1, "tags": [ [ "p", "97f848adcc4c6276685fe48426de5614887c8a51ada0468cec71fba938272911", "wss://nostr.oxtr.dev/", "Rizful.com" ], [ "p", "9989500413fb756d8437912cc32be0730dbe1bfc6b5d2eef759e1456c239f905", "wss://relay.snort.social/", "nostr.build" ], [ "p", "20986fb83e775d96d188ca5c9df10ce6d613e0eb7e5768a0f0b12b37cdac21b3", "wss://nostr.zebedee.cloud/", "YakiHonne" ], [ "p", "532d830dffe09c13e75e8b145c825718fc12b0003f61d61e9077721c7fff93cb", "wss://nos.lol/", "primal" ], [ "p", "3efdaebb1d8923ebd99c9e7ace3b4194ab45512e2be79c1b7d68d9243e0d2681", "wss://nos.lol/", "damus" ], [ "p", "3bf0c63fcb93463407af97a5e5ee64fa883d107ef9e558472c4eb9aaaefa459d", "wss://relay.westernbtc.com/", "fiatjaf" ], [ "p", "fa984bd7dbb282f07e16e7ae87b26a2a7b9b90b7246a44771f0cf5ae58018f52", "wss://pyramid.fiatjaf.com/", "PABLOF7z" ], [ "p", "d61f3bc5b3eb4400efdae6169a5c17cabf3246b514361de939ce4a1a0da6ef4a", "wss://nos.lol/", "miljan" ], [ "e", "fdd968dadbee59a00be110a70d158e436f583d97a9e18e18b7aa7f36504b6bed", "wss://algo.utxo.one/", "root" ], [ "e", "f492874a2ad58e123ac09ef30936f66d4b3ac8d688e33efa6ee30cd936b2a4ce", "", "mention" ], [ "e", "21d853a1dec1a2ddfff95313851f11ca3a7b6b204e84d80cf18b492927279d6e", "wss://nostr.wine/", "reply", "97f848adcc4c6276685fe48426de5614887c8a51ada0468cec71fba938272911" ], [ "client", "Coracle", "31990:97c70a44366a6535c145b333f973ea86dfdc2d7a99da618c40c64705ad98e322:1685968093690" ] ], "content": "It's a totally different approach, but maybe you're right, good LLMs are relatively new and maybe could be considered to supersede fuzzy hashing. But the main problem of reverse-engineering the compression algorithm (which is one way to think about llms) still exists. If you're thinking of working on this I'm happy to see what I can do to help.", "sig": "ee03a9b29826ac4ee3a99533490b75be5bc319d62d6415a9de82a75a5f63c89873f591994757e9b10e49abe9a07a9e9268ad21698ae24ce0e41ef54942f4116f" }

hodlbod on Nostr: It's a totally different approach, but maybe you're right, good LLMs are relatively ...