Google open-sources Harness2 framework for improving AI agents
MarkTechPost: Google Open-Sources Harness2, a Recursive Agent Harnessing Framework
Google Cloud AI Research has open-sourced Harness². It is a recursive agent harnessing framework that improves the code and files around a frozen model. For developers, the pitch is simple. Your agent may get better without a better model. TL;DR Size: A framework, not a model. 0 parameters trained; 8 editable harness components. Version 0.1.0. Runs on: Linux with Python 3.12 or 3.13 and uv. Model runs call models through Vertex AI. GPU requirement: Not disclosed. Performance: 1 ref
Get smart on it
Harness² is a framework that improves an AI agent's performance by refining the components around a frozen model, such as prompts, tools, memory, and skills, rather than by retraining the model itself. The framework uses a two-level recursive process where it proposes alternative configurations, tests them against the original setup, and keeps only changes that show measurable behavioral improvements. Testing on professional benchmarks showed that a single refinement step improved performance across all tested configurations, with some models gaining up to 11.5 points. The framework is designed to work in open-world settings where tasks are unseen and no ground-truth labels exist to verify correct answers.
Explainer: The 90% That Matters: Why Your Agent's Harness Beats the Model
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Replit is no longer working with Anthropic, CEO says
Over the weekend, Masad clarified that OpenAI would replace Anthropic as its default model provider. Claude will still be available to customers on the platform.
ServiceNow AI Control Tower: Selling a penthouse while building the frame
ServiceNow Inc. is making one of the more consequential and visible bets in enterprise AI. The company says AI Control Tower can discover and govern any agent, work across models and clouds, track cost and value, and shut down behavior that violates policy. That sales pitch plays directly to ServiceNow’s greatest asset – its installed […] The post ServiceNow AI Control Tower: Selling a penthouse while building the frame appeared first on SiliconANGLE.
ChatGPT can peek at your Chrome tabs now
OpenAI's ChatGPT Atlas browser is gone, but now ChatGPT's Google Chrome extension is getting some upgrades that allow it to use the browser tabs you already have open. With the extension installed, OpenAI says ChatGPT can now view your browser tabs when you tag Chrome in ChatGPT's web or desktop app, posting a demo video showing someone asking ChatGPT to compare the three tabs they have open with sofas they're considering. A few big upgrades for Chrome users today! We're bring
Also reported by The Decoder
Bringing GPT-Rosalind to academic research labs
Introducing the Rosalind Academic Plan, offering eligible academic labs sponsored access to GPT-Rosalind and tools to advance life sciences research.
Also reported by The Decoder
Amazon’s Bee launches two new personal AI devices, starting at $75
Amazon-owned Bee has launched its first new AI devices since its acquisition, including an updated wearable and a credit-card-sized recorder that attaches to smartphones. The devices can summarize conversations, create to-do lists, and integrate with Alexa and Amazon shopping, with prices starting at $74.99.
Also reported by The Verge
Perplexity Open-Sources SPACE, a Firecracker MicroVM Sandbox for AI Agents
Perplexity has open-sourced SPACE, the sandbox platform behind every task in Perplexity Computer. The Perplexity SPACE sandbox gives each agent task its own Firecracker microVM. Credentials and outbound traffic are controlled from outside that VM. The code ships under Apache 2.0 on GitHub. For teams building coding or browsing agents, this is a production-tested isolation layer they can self-host. TL;DR Size: Rust codebase, release 0.8.0, the public baseline. HTTP API plus server-sent ev