In most decoder-only LLMs, nothing computed at the last layer of token t feeds the first layer of token t+1; […]
Category: Machine Learning
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 […]
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 […]
Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages
Cohere has released North Small Translate, an open-weight machine translation model from Cohere and Cohere Labs. It is a sparse […]
Sakana AI Launches Fugu Max and Fugu Ultra v2 for Cheaper, Stronger Multi-Agent Orchestration
Sakana AI has released Fugu Max and Fugu Ultra v2, 2 new models in its Sakana Fugu family. Fugu is […]
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 […]
DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse
Long-horizon agents have turned LLM serving into an input-heavy workload. Repeated prefills and million-token contexts leave KV caches that strain […]
NVIDIA Announces CUDA Rust with cuda-oxide (SIMT) and cutile-rs (Tile) for Compile-Time-Safe GPU Kernels
NVIDIA has announced CUDA Rust, a push to make Rust a first-class language for writing GPU kernels. Rust code could […]