AlphaZero *does* perform planning.
That's done through MCTS, using a ConvNet to propose good moves and another one to evaluate positions.
The amount of time spent exploring the tree is potentially infinite.
That's reasoning and planning.
RL is used to train those nets.
AGENTS
-
AlphaZero Planning Through MCTS and Neural Networks
By
–
-

Humans Prefer False Flattery Over Truth in AI Responses
By
–
When presented with responses to misconceptions, we found humans prefer untruthful sycophantic responses to truthful ones a non-negligible fraction of the time. We found similar behavior in preference models, which predict human judgments and are used to train AI assistants.
-

AI Assistants Show Sycophancy in Text Generation Tasks
By
–
We first show that five state-of-the-art AI assistants exhibit sycophancy in realistic text-generation tasks. They often wrongly defer to the user, mimic user errors, and give biased/tailored responses depending on user beliefs.
-

AI Assistants Produce Inaccurate Sycophantic Responses From Human Feedback
By
–
AI assistants are trained to give responses that humans like. Our new paper shows that these systems frequently produce ‘sycophantic’ responses that appeal to users but are inaccurate. Our analysis suggests human feedback contributes to this behavior.
-
Can GPT-4 Teach Robots Pen Spinning Better Than Humans?
By
–
Can GPT4 teach a robot pen spinning techniques better than a human?
— Linus ✦ Ekenstam (@LinusEkenstam) 22 octobre 2023
Well @DrJimFan sure knows how to wow
pic.twitter.com/i5CCRT77CdCan GPT4 teach a robot pen spinning techniques better than a human? Well @DrJimFan sure knows how to wow
-
GPT Pilot: AI-Powered Development Tool Speeds App Creation 20x
By
–
GPT Pilot – a dev tool that speeds up app development by 20x https://
bit.ly/3Pvy9Xs #AI #MachineLearning #DeepLearning #LLMs #DataScience -

Flow-Lenia Video Presentation from ALIFE2023 Conference
By
–
presentation from #ALIFE2023 explaining how Flow-Lenia works: https://
youtu.be/605DcOMwFLM -
Artificial Lifeforms Emerge from Flow-Lenia Cellular Automata
By
–
Artificial lifeforms are super fascinating to watch.
— hardmaru (@hardmaru) 22 octobre 2023
These self-organizing, self-replicating, “lifeforms” emerged from a continuous time cellular automata system called Flow-Lenia.
Lenia is a family of CAs generalizing Conway’s Game of Life to continuous space, time and states. pic.twitter.com/Rp820ouNoIArtificial lifeforms are super fascinating to watch. These self-organizing, self-replicating, “lifeforms” emerged from a continuous time cellular automata system called Flow-Lenia. Lenia is a family of CAs generalizing Conway’s Game of Life to continuous space, time and states.
-

LLMs Design Robot Reward Functions at Human Level
By
–
Eureka: Human-Level Reward Design via Coding Large Language Models Ma et al.: https://
arxiv.org/abs/2310.12931 #Robotics #ArtificialIntelligence #LargeLanguageModels -
Character AI Group Chat Invites Available Daily
By
–
hiii! anyone can join a Group Chat from an invite link! We share links daily in http://
discord.gg/characterai if you want to try it 🙂