RCI (Reflect, Critique, Improve) Prompting I haven’t explored this concept too much for jailbreaks but it allows GPT to review its own outputs and fix issues/flaws one area of application this is already immediately helpful is "self-healing" coding and basic reasoning problems
RESEARCH
-
LLMs as Pre-trained Emulators Without Reinforcement Learning
By
–
It’s actually all just pre-trained LLM, not RL at all. The thing is, LLMs are already good emulators of people.
-
Is AI Really Intelligent? Morozov Questions Definition
By
–
The problem with artificial intelligence? It’s neither artificial nor intelligent | Evgeny Morozov "Human intelligence is not one-dimensional. It rests on what the 20th-century Chilean psychoanalyst Ignacio Matte Blanco called bi-logic" https://
bit.ly/3M62Jqp -
Why Emergence Occurs in Larger AI Models
By
–
I don't have a great answer to "why emergence occurs", but here's a handwavy thought:
Many emergent abilities require multi-step reasoning, more knowledge, knowing how to do "tail-end" or rare tasks, and larger models are somewhat better at all of these things. With their -
Paper published in TMLR with survey certification
By
–
Yep, and here is the our paper in TMLR (with survey certification):
-
AutoGPT Agents Create Emergent Open Worlds for Indie Games
By
–
Love it – much fertile soil for indie games populated with AutoGPTs, puts "Open World" to shame. Simulates a society with agents, emergent social dynamics.
Paper: https://
arxiv.org/abs/2304.03442
Demo: https://
reverie.herokuapp.com/arXiv_Demo/#
Authors: @joon_s_pk @msbernst @percyliang @merrierm et al. -
Cerebras-GPT Model Family Trends on Hugging Face
By
–
We are excited to see a Cerebras-GPT model trending on Hugging Face! Check out our page on Hugging Face to see the entire family of models: https://
hubs.ly/Q01KRZzT0 -
AI Leaders Discuss LLMs, ChatGPT and Vectara’s Vision
By
–
In the latest Stories in AI episode, I speak with @awadallah -Founder of Vectara and is one of the industry leaders who gave us Hadoop and #bigdata as we know today. We dive deep into what is really going on behind the scenes with LLMs, ChatGPT and oth…
-
First Black Hole Image: AI Processing Breakthrough by Katie Bouman
By
–
#otd in 2019 scientists released the first-ever photo of a black hole. Here’s the moment that Prof. Katie Bouman and colleagues first processed the image: https://
nyti.ms/2D9Wr4B -
Edward Frenkel on Mathematics and Quantum Physics
By
–
Here's my conversation with Edward Frenkel (
@edfrenkel
), a mathematician at UC Berkeley, working on the interface of mathematics and quantum physics. Ed is a brilliant mind and a truly special human being. This was challenging, moving, and fun! https://
youtube.com/watch?v=Osh0-J
3T2nY
…