Code execution with MCP: Building more efficient agents
simonwillison.net·1h
💻Programming
Flag this post
Parallel achieves 70% accuracy on SEAL, benchmark for hard web research
📐Computational geometry
Flag this post
Beyond Standard LLMs
🧩Procedural Generation
Flag this post
Low-Level Hacks
🧱Data structures
Flag this post
OpenSIR: Open-Ended Self-Improving Reasoner
arxiv.org·20h
🧩Procedural Generation
Flag this post
Adding New Capability in Existing Scientific Application with LLM Assistance
arxiv.org·20h
🧩Procedural Generation
Flag this post
OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data
arxiv.org·20h
🧩Procedural Generation
Flag this post
Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
arxiv.org·20h
🧩Procedural Generation
Flag this post
Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization
arxiv.org·20h
📈Vectorization
Flag this post
Engineering.ai: A Platform for Teams of AI Engineers in Computational Design
arxiv.org·20h
🧩Procedural Generation
Flag this post
Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
arxiv.org·20h
🧱Data structures
Flag this post
Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?
arxiv.org·20h
📐Computational geometry
Flag this post
Playing Around with ARM Assembly
💻Programming
Flag this post
Loading...Loading more...