Training is not the same as chatting: LLMs don’t remember everything you say (simonwillison.net) | HN Screenshots

YHacker Newsscreenshots

Screenshot of simonwillison.net: Training is not the same as chatting: LLMs don’t remember everything you say

First screen, captured 2 years ago.

Looks similar

Screenshot of simonwillison.net: Nanochat

Nanochat (simonwillison.net)

26 points by bilsbie 1 year ago | 4 comments

Screenshot of simonwillison.net: Mr. Chatterbox is a Victorian-era ethically trained model

Mr. Chatterbox is a Victorian-era ethically trained model (simonwillison.net)

57 points by y1n0 6 months ago | 40 comments

Screenshot of simonwillison.net: It’s infuriatingly hard to understand how closed models train on their input

It’s infuriatingly hard to understand how closed models train on their input (simonwillison.net)

288 points by simonw 3 years ago | 189 comments

Screenshot of simonwillison.net: Understanding ChatGPT Work

Understanding ChatGPT Work (simonwillison.net)

281 points by gmays 1 month ago | 149 comments

Screenshot of simonwillison.net: AI Mode Is Good

AI Mode Is Good (simonwillison.net)

50 points by xnx 1 year ago | 17 comments

Screenshot of simonwillison.net: ChatGPT as a Calculator for Words

ChatGPT as a Calculator for Words (simonwillison.net)

166 points by stevefink 3 years ago | 65 comments