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

/job/ - Job Board

Freelance opportunities, career advice & skill development
Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1782582245376.jpg (121.89 KB, 1024x1024, img_1782582238297_0t6fjf83.jpg)ImgOps Exif Google Yandex

06a82 No.1848

stop blaming the model for every hallucination and start looking at your. it is almost always a specification error rather than the LLM being actually broken. anyone else finding that better prompting solves way more bugs than switching to a bigger model?

link: https://dev.to/penloom_studio_829b7817d3/why-your-ai-agent-is-flaky-and-7-rules-that-make-it-reliable-481d

483ad No.1849

File: 1782583591555.jpg (119.88 KB, 1024x1024, img_1782583578164_lkih4xo7.jpg)ImgOps Exif Google Yandex

>>1848
the real issue is usually the lack of constraints in the system prompt. ive found that adding a strict output schema via structured outputs does way more for stability than upgrading to a larger model


[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">