Fire in the Hole! Benchmarking is broken
🚀Performance
Flag this post
A reminder to stay in control of your agents
🏗️Cranelift
Flag this post
Weight-sparse transformers have interpretable circuits
lesswrong.com·5h
🤖Transformers
Flag this post
Chaotic Creation: Building Intelligent Networks from Noise by Arvind Sundararajan
🔲Cellular Automata
Flag this post
A catalog of side effects
🦀Rust Macros
Flag this post
Evaluating LLMs' Reasoning Over Ordered Procedural Steps
arxiv.org·3d
🧮SMT Solvers
Flag this post
Show HN: PolyCouncil: Multi-Model Deliberation Engine for LMStudio (Open Source)
🦙Ollama
Flag this post
Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
arxiv.org·1d
🎯Reinforcement Learning
Flag this post
ClaudoBiography: The Unauthorized Autobiography of Claude, or: The Life of Claude and of His Fortunes and Adversities
lesswrong.com·9h
💫Effect Systems
Flag this post
Enabling Agents to Communicate Entirely in Latent Space
arxiv.org·18h
📱Edge AI
Flag this post
DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
arxiv.org·1d
💬Prompt Engineering
Flag this post
Show HN: General Intelligence – Active knowledge framework for machine learning
🤖Transformers
Flag this post
Undissolvable Problems: things that still confuse me
lesswrong.com·1d
∘Category Theory
Flag this post
Loading...Loading more...