In this tutorial, we build an end-to-end hierarchical Neural Radiance Field (NeRF) using JAX, Flax, Optax, and the volume-rendering primitives […]
Category: Staff
A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth
In most decoder-only LLMs, nothing computed at the last layer of token t feeds the first layer of token t+1; […]
AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents
AWS introduced Pizza Bot, as a self-hosted application for AI tasks that continue while users work elsewhere. It organizes completed […]
Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks
An agent, in its simplest form, is an LLM calling tools in a loop. That loop works for short jobs. […]
Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost
Cognition, the company behind the Devin coding agent, has released SWE-2, its most capable coding model to date. SWE-2 is […]
Fly Language Model (FLM) Wires the Full Fruit Fly Connectome Into a Frozen 1.2B LLM, and Its Own Controls Show the Wiring Does Not Help
The Fly Language Model (FLM) is a public chatbot that couples the complete retained MaleCNS v1.0 fruit fly connectome to […]
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
An agent harness is the code around a model: execution loop, tools, context, state, recovery, and verification. Per the Terminal-Bench […]
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills
Anthropic has published a new plugin evals workflow for Claude Code. The claude plugin eval command runs a plugin against […]
Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation
Training an LLM to call tools reliably requires datasets that pair user queries with correct tool-use chains. Producing that data […]
NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100
Biomolecular structure prediction has shifted from single-target runs to proteome-scale worklists. The bottleneck is no longer whether a model can […]