AI Agents
AI Agent technology and applications
Articles
Hierarchical NeRF with JAX3D: Volumetric Rendering, Novel-View⭐8
Build an end-to-end hierarchical NeRF in JAX with JAX3D: volumetric rendering, importance sampling, training, novel-view synthesis, 360° rendering, and marching...
Princeton Researcher Proposes Recurrent Looped Transformer (RLT)⭐7
Princeton's Recurrent Looped Transformer (RLT) carries decoder state and SWA cache across tokens, with no reset. A design spec for unbounded recurrent depth.
AWS Launches Pizza Bot: An Open Source Inbox for Background AI Agents⭐9
AWS Pizza Bot is an open source inbox for async AI agents, organizing completed work and pending approvals into an email-style view with scheduling and webhooks...
Context Engineering Inside the Harness: 4 Mechanisms That Beat⭐7
Long-horizon AI agents fail from context overflow and goal loss. Learn how compaction, memory, budgeting, and todo-state in the harness fix it.
GPU-Accelerated Machine Learning with NVIDIA cuML and RAPIDS:⭐9
Explore NVIDIA cuML and RAPIDS for GPU-accelerated machine learning, covering benchmarking, explainability, clustering, and model inference in this tutorial.
Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model⭐7
Cognition's SWE-2 coding model, post-trained from Kimi K3, hits 50.0% on FrontierCode 1.1, matching Fable 5.1 at 64% lower cost and running only inside Devin.
Fly Language Model (FLM) Wires the Fruit Fly Connectome Into a⭐7
The Fly Language Model wires the fruit fly connectome into a frozen 1.2B LLM via a reservoir readout it trains on its own—yet its controls show the fly wiring d...
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed's⭐9
ByteDance Seed's HarnessDev tests whether LLMs can build and evolve their own agent harness, finding only 34 of 64 changes generalize to unseen tasks.
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No⭐7
Anthropic's `claude plugin eval` command for Claude Code runs plugin evals with six grader types, a no-plugin baseline, and a CI gate for skills.
Sakana AI Unveils Fugu Max and Fugu Ultra v2: Cheaper, Stronger⭐7
Sakana AI launches Fugu Max and Fugu Ultra v2, cheaper multi-agent orchestration models that balance capability and cost via a learned orchestrator API.