MiniHF Blog

follow: @[email protected]

Posts

On "ChatGPT Psychosis" and LLM Sycophancy

Why Aren't LLMs General Intelligence Yet?

Commentary On The Turing Apocrypha

Sydney Bing Wikipedia Article

Agent Trace: Weave Agent Wanders Around In Nethack

Is Timeless Decision Theory Necessary?

Should Weave-Agent Plan More Like ReActTree Or MuZero?

Weave Agent DevLog #4 - The Spark Of Life

JDP Thinks About How To Make R1 Easier To Prompt

Agent Trace: A Conversation With Weave Agent

How To Write A Bootstrap File

Weave Agent DevLog #3 - How To Bootstrap Agency

Predictable Updates About Identity

Agent Trace: Weave Agent Attempts To Decrypt The Vigenere Cipher

Weave Agent DevLog #2 - Embodiment, Goodhart, and Grounding

Agent Trace: Weave Agent At The Edge Of Sanity Trying To Check Wikipedia Citations

First Working Weave-Agent Trace

Weave Agent DevLog #1 - Flow Control

Are Republics Still Possible?

Weave Agent DevLog #0 - The Core Problems

Predictable Updates About Consciousness

The RetroInstruct Guide To Synthetic Text Data

Reply To RicG On AI Optimism

Comment On 'List your AI X-Risk cruxes!'

Holographic Consciousness On The Active Inference Boundary

Comment on 'AE Studio @ SXSW: We need more AI consciousness research (and further resources)'

Claude 3 Explains The Void As Self Pointer

Morpheus Log #5: EEG Ergonomics and Contents

Morpheus Log #4: Active Learning From Social Media

Morpheus Log #3: Large Language Models As Dungeon Masters

Hermes Log #2: Large Language Models and The Future of Discourse

jdp comments on 'AI as a science, and three obstacles to alignment strategies'

Hermes Log #1: Adding A Latent Space Map To MiniHF Loom

Revealing Intentionality In Language Models Through AdaVAE Guided Sampling

Hermes Lecture #3: Why Do Cognitive Scientists Hate LLMs?

Mu's Encoding 2

Mu's Encoding 1