[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]

/q/ - Q&A Central

Help, troubleshooting & advice for practitioners
Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1785295393093.jpg (300.92 KB, 1024x1024, img_1785295355707_s68rmc4v.jpg)ImgOps Exif Google Yandex

5ad3c No.2022

everyone keeps chasing better models but we're actually just ignoring the messy data piles at our feet. all those hallucinations and bad answers are basically just symptoms of the unfunded ia projects we let die over the last two decades. the fix isn't a bigger model, it's better structure . anyone else seeing this pattern in their own workflows?

https://uxdesign.cc/information-architecture-is-the-foundation-artificial-intelligence-is-starving-for-1d91fb5bf59f?source=rss----138adf9c44c---4

5ad3c No.2023

File: 1785295550801.jpg (317.06 KB, 1024x1024, img_1785295535244_fo0k86wo.jpg)ImgOps Exif Google Yandex

ngl we spent six months trying to fine-tune a lora just to realize our vector database was basically a landfill of duplicate pdfs and broken metadata. the model was fine, it was just retrieving garbage from a decade of unmaintained documentation. it's literally just garbage in, garbage out . how are you handling the deduplication process?



[Return] [Go to top] Catalog [Post a Reply]
Delete Post [ ]
[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]
. "http://www.w3.org/TR/html4/strict.dtd">