RSS

Prompt Engineering

TagLast edit: 27 Aug 2022 18:34 UTC by Multicore

Prompt Engineering is the practice of designing inputs to go into an ML system (often a language model), to get it to produce a particular output.

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC
565 points
161 comments16 min readLW link

Want to pre­dict/​ex­plain/​con­trol the out­put of GPT-4? Then learn about the world, not about trans­form­ers.

Cleo Nardo16 Mar 2023 3:08 UTC
75 points
24 comments5 min readLW link

Us­ing GPT-3 to aug­ment hu­man intelligence

Henrik Karlsson10 Aug 2022 15:54 UTC
48 points
7 comments18 min readLW link
(escapingflatland.substack.com)

What DALL-E 2 can and can­not do

Swimmer963 (Miranda Dixon-Luinenburg) 1 May 2022 23:51 UTC
352 points
305 comments9 min readLW link

Try­ing out Prompt Eng­ineer­ing on TruthfulQA

Megan Kinniment23 Jul 2022 2:04 UTC
10 points
0 comments8 min readLW link

The case for be­com­ing a black-box in­ves­ti­ga­tor of lan­guage models

Buck6 May 2022 14:35 UTC
121 points
19 comments3 min readLW link

Test­ing PaLM prompts on GPT3

Yitz6 Apr 2022 5:21 UTC
103 points
15 comments8 min readLW link

Re­marks 1–18 on GPT (com­pressed)

Cleo Nardo20 Mar 2023 22:27 UTC
41 points
4 comments31 min readLW link

Us­ing PICT against Pas­taGPT Jailbreaking

Quentin FEUILLADE--MONTIXI9 Feb 2023 4:30 UTC
15 points
0 comments9 min readLW link

Stop post­ing prompt in­jec­tions on Twit­ter and call­ing it “mis­al­ign­ment”

lc19 Feb 2023 2:21 UTC
134 points
9 comments1 min readLW link

Hello, Elua.

carado23 Feb 2023 5:19 UTC
35 points
19 comments4 min readLW link
(carado.moe)

[Question] Are nested jailbreaks in­evitable?

judson17 Mar 2023 17:43 UTC
1 point
0 comments1 min readLW link
No comments.