Bringing AI to the next generation of fusion energy
We’re partnering with Commonwealth Fusion Systems (CFS) to bring clean, safe, limitless fusion energy closer to reality.
Training Software Engineering Agents and Verifiers with SWE-Gym
We present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and a task specified in natural language. We use SWE-Gym to train language model based SWE agents, achieving up to 19% absolute gains in …
Read more “Training Software Engineering Agents and Verifiers with SWE-Gym”
Iterative fine-tuning on Amazon Bedrock for strategic model improvement
Organizations often face challenges when implementing single-shot fine-tuning approaches for their generative AI models. The single-shot fine-tuning method involves selecting training data, configuring hyperparameters, and hoping the results meet expectations without the ability to make incremental adjustments. Single-shot fine-tuning frequently leads to suboptimal results and requires starting the entire process from scratch when improvements are …
Read more “Iterative fine-tuning on Amazon Bedrock for strategic model improvement”
Announcing prompt management in the Vertex AI SDK
As generative AI applications grow in sophistication, development workflows become more fragmented. Although AI can be a force multiplier, teams may design prompts in one environment, manage versions in spreadsheets or text files, and then manually integrate them into their code. This leads to inefficiencies, versioning chaos, and collaboration bottlenecks. Vertex AI Studio is designed …
Read more “Announcing prompt management in the Vertex AI SDK”
How Anthropic’s ‘Skills’ make Claude faster, cheaper, and more consistent for business workflows
Anthropic launched a new capability on Thursday that allows its Claude AI assistant to tap into specialized expertise on demand, marking the company’s latest effort to make artificial intelligence more practical for enterprise workflows as it chases rival OpenAI in the intensifying competition over AI-powered software development. The feature, called Skills, enables users to create …
Why the F5 Hack Created an ‘Imminent Threat’ for Thousands of Networks
Networking software company F5 disclosed a long-term breach of its systems this week. The fallout could be severe.
Method teaches generative AI models to locate personalized objects
Say a person takes their French Bulldog, Bowser, to the dog park. Identifying Bowser as he plays among the other canines is easy for the dog owner to do while onsite.
An experiment with “realism” with Wan2.2 that are safe for work images
Got bored seeing the usual women pics every time I opened this sub so decided to make something a little friendlier for the work place. I was loosely working to a theme of “Scandinavian Fishing Town” and wanted to see how far I could get making them feel “realistic”. Yes I am aware there’s all …
Read more “An experiment with “realism” with Wan2.2 that are safe for work images”
Introducing Veo 3.1 and advanced creative capabilities
We’re rolling out significant updates to Veo that give people even more creative control.
Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent …
Read more “Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration”