NVIDIA announced the BioNeMo Agent Toolkit, integrated with Anthropic's Claude Science, enabling scientists to use natural language to run accelerated AI workflows in drug discovery, genomics, and more. The toolkit includes GPU-accelerated tools like Parabricks, RAPIDS-singlecell, and nvMolKit, and is used by 18 of the top 20 pharmaceutical companies. Claude Science is now in public beta.

shot-scraper video is a new command that lets coding agents record video demos of their work. It takes a YAML storyboard, runs it via Playwright, and produces a video. The article details an example using Datasette and how the feature was developed with AI assistance.

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights. Across 52 evaluation cells, SkillOpt achieves best or tied-best results, and the optimized skills remain compact, auditable, and transferable.

This post walks through how AG-UI integrates into the Fullstack AgentCore Solution Template (FAST) to build interactive agent frontends on Amazon Bedrock AgentCore. We then show how CopilotKit extends this with generative UI, shared state, and human-in-the-loop interactions, all deployed on Amazon Bedrock AgentCore.

This post presents five practical patterns for building resilient generative AI applications on AWS, progressing from native Amazon Bedrock features to multi-model orchestration using an LLM gateway. These patterns address real-world challenges such as quota exhaustion during traffic surges, maximizing availability through geographic distribution, and preventing noisy neighbor problems in multi-tenant environments.

Outpost VFX achieved 8x faster training speeds for face replacement AI models by migrating to AWS multi-GPU infrastructure, reducing initial client delivery from 1-2 weeks to 2 days.

IBS Software used Amazon Bedrock's managed distillation capabilities to build a cost-effective bilingual NER system for cargo logistics. By distilling knowledge from Amazon Nova Pro into Nova Lite, they achieved 95.085% F1-Score while reducing operational costs by 14x. This post details the technical approach, challenges, and deployment architecture.

Learn how fine-tuning Amazon Nova models using Amazon SageMaker AI addresses issues like hallucinations and cost, achieving up to 94.77% extraction accuracy and 50% cost reduction.

Evaluating long-running, stateful agents requires a new eval runner. Harbor integrates with LangChain's Deep Agents, LangSmith sandboxes, and observability to provide scalable, isolated evaluations with explainable traces.

Release of shot-scraper 1.10 with a new video storyboard feature for recording demos.

NVIDIA's inference software stack, co-designed with GPUs, CPUs, networking, and systems and strengthened by open source, continuously improves hardware performance. On Blackwell, it reduced token costs by up to 5x for DeepSeek V4 in one month. The article details how software optimizations across production operations, application acceleration, and infrastructure access compound to lower cost per token.

Jaiveer Singh leads NVIDIA's Isaac ROS team, building open-source infrastructure for robotics on ROS 2 with CUDA acceleration. His journey from LEGO Mindstorms to leading a team whose intern project became Isaac ROS highlights the power of open source and NVIDIA's long-term vision in physical AI.

The article introduces 'Wiki Memory' as a pattern for agent memory, where agents transform raw source data into a compact, persistent, and structured knowledge layer. Unlike RAG, it precomputes a higher-level synthesis. Examples include DeepWiki, Karpathy's LLM Wiki, and Factory's AutoWiki. The article also discusses open questions about raw data, compression format, and maintenance, concluding that files and agents are common answers.

This article argues that specialization is an inevitable consequence of finite resources and selection pressure, drawing from optimization theory (No Free Lunch theorems), evolutionary biology, competitive markets, and machine learning. It distinguishes specialization from domain knowledge and addresses the Bitter Lesson, concluding that scaling does not eliminate the need for focused systems.