Post Content
In this video I will look at why LLMs hallucinate. LLMs hallucinate not because they’re “broken,” but because today’s training and accuracy-only evaluations incentivize guessing. This is based on a new research from OpenAI.
https://openai.com/index/why-language-models-hallucinate/
https://cdn.openai.com/pdf/d04913be-3f6f-4d2b-b283-ff432ef4aaa5/why-language-models-hallucinate.pdf
https://claude.ai/public/artifacts/557007ce-c731-460e-b6ea-152718774cca
https://claude.ai/public/artifacts/9f1238f1-0efc-4880-974a-29d1f42029b3
https://claude.ai/public/artifacts/67698ee1-18a9-4251-b408-83c0876015eb
https://claude.ai/public/artifacts/606fc46e-9750-4d27-9f48-633cb0cff7eb
Website: https://engineerprompt.ai/
RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag
Let’s Connect:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
TIMESTAMP
00:00 Hallucinations in Language Models
00:48 How Language Models Work
02:26 The Issue with Next Word Prediction
02:50 Evaluation Mechanisms and Their Flaws
04:11 Proposed Solutions to Mitigate Hallucinations
07:16 Observations and Claims from OpenAI’s Paper Read More Prompt Engineering
#AI #promptengineering
