Blog
Notes and analysis on AI development.
JetPack 7.2 brings one-command NemoClaw deployment to Jetson
NVIDIA JetPack 7.2 packages NemoClaw, Jetson agent skills, Yocto support, MIG, and Orin Super Mode for physical AI agents at the edge.
Google SRE reveals AI Operator for production incident response
Google SRE has published its AI-Ops design for AI Operator, Actus, Detectr, and controlled autonomous production mitigation.
JetBrains Opens Mellum2 to Cut Coding Agent Call Costs
JetBrains Mellum2 is a 12B MoE model that activates 2.5B parameters per token. It adds a private coding model option for IDE and agent workflows.
Skipper launches as a test of coding agents without review
SkipLabs has launched Skipper, a beta coding agent that turns one prompt into a running backend service through a closed-loop generation and verification process.
AWS Transform processed 4.5B lines, then moved modernization agents into Codex and Claude
AWS Transform agents now run through Kiro, Claude Code, Cursor, Codex, plugins, and MCP, with AWS claiming 4.5B+ processed lines and 1.6M+ saved hours.
NVIDIA Bundles a 550B Open Model With an Agent Runtime Stack
NVIDIA introduced Nemotron 3 Ultra alongside NemoClaw, OpenShell, and CUDA-X agent skills, pushing open agent competition into the runtime layer.
BlueField-4 STX puts agent memory security into silicon
NVIDIA added DOCA Vault, Argus, and Flow security controls to BlueField-4 STX, moving AI agent data policy into storage and DPU paths.
OpenAI models and Codex are now generally available on Amazon Bedrock
OpenAI GPT-5.5, GPT-5.4, and Codex are generally available on Amazon Bedrock, shifting authentication, billing, and feature boundaries into AWS.
NVIDIA opens a 32B robotaxi model and closed-loop training stack
NVIDIA Alpamayo 2 Super ties a 32B VLA teacher model to AlpaGym, OmniDreams, CoC auto-labeling, and agent skills for L4 robotaxi development.
QVAC 0.12.0 brings TurboQuant to local KV cache pressure
Tether announced QVAC SDK 0.12.0 with TurboQuant support. The useful question is how KV cache compression changes local long-context AI.
AgentCore A/B testing turns prompt edits into release experiments
AWS AgentCore Optimization preview productizes agent quality loops with trace-based recommendations, batch evals, and A/B testing.
DGX Station for Windows puts trillion-parameter AI on the enterprise desk
NVIDIA introduced DGX Station for Windows with GB300, 784GB coherent memory, and dual boot for enterprise AI agent workstations.