Coding iteratively starting with "generated knowledge" — a similar approach may be used to have the LLM write a book. An example of LLM prompting for programming https://
bit.ly/41H00bD
PROMPT ENGINEERING
-
Iterative LLM Programming with Generated Knowledge Approach
By
–
-
Test Benchmark Rerun and Jailbreak Submissions Review
By
–
reran the test benchmark after a lot of complaints it wasn't working as well anymore & those other ideas are good and I have thought abt them somewhat in regard to the pending jailbreaks, there are a LOT of junk jailbreaks that are submitted to me in regard to the comments, I
-
AI Model Looping Issues and Credit Card Limits
By
–
il faut avoir une CB no limit pour qu'il aille au bout de son délire, parfois il boucle sur des conneries et du coup il génère du contenu de façon infinie sur les retours que j'avais vu, mais y'a @nguyen_nico qui l'a un peu poncé semaine dernière il a fait un tuto
-
LLMs for High Level Planning and Context Assumption
By
–
Yes, we are using LLMs for high level planning, like that “bring me coffee” example. Especially because LLMs seem to assume the right context even if we don’t specify it. But here I am not talking about the edge cases when the assumptions fail.
-
Reverse Instructions Method Naming Discussion Paper
By
–
Its nice to see someone write this paper. A small nit is that I think the naming doesn't do the method justice. Why is this called "Longform"? Something nicer might be something like "reverse instructions" or prompt inversion.
-
Emergence and Reasoning in Large Language Models Talk
By
–
Emergence and reasoning in large language models – A talk This is a great talk by @_jasonwei on the emergent abilities of large language models(LLMs), chain-of-thought prompting, and other related topics. Video(YT): https://
youtube.com/watch?v=0Z1ZwY
2K2-M
… Slides: https://
self-supervised.cs.jhu.edu/fa2022/files/j
asonwei-CoT-emergence-talk-JHU.pdf
… -
LLM to LLM Conversations Need World Controller for Better Results
By
–
I tried LLM to LLM conversations and the results are a bit underwhelming. Cyclical boring conversation after a while. A world controller is necessary
-
AutoGPT and BabyAGI: Progressive AI Agent Mastery
By
–
tu décroches un week-end avec l'AI, tu termines la semaine avec du #autogpt et de #babyAgi, et t'en es déjà au #godmode
-
Crazy Midjourney tip but controversial, your opinion?
By
–
This #Midjourney tip is crazy… But controversial → https://youtu.be/f8xVJwWAanQ What do you think? #Midjourneyv5 #MidjourneyArt
-
Using GPT to Control Character Animations Based on Emotional State
By
–
> download 50 mixamo animations
> give all their names to GPT
> ask it to output one depending on what it is feeling > play anim in Unreal as conversation happens
> holy shit