Agent harness choice affects AI task performance
Hugging Face: Same Model, Different Harness: CUGA, Hermes, and Deep Agents, When to Pick CUGA?
Organizations deploying AI agents must choose between frameworks that use identical underlying models but differ in architecture, affecting speed, cost, and integration complexity.
Get smart on it
There are nearly 200 agent harnesses available, which are the software frameworks that control how AI models operate on tasks. A controlled experiment tested three different harnesses using the same AI model on the same set of tasks, and the results showed that task completion rates varied dramatically depending on which harness was used, ranging from 30 percent to 81 percent. This demonstrates that the harness itself matters as much as the underlying model for determining performance. CUGA is an open-source harness designed specifically for enterprise work, where agents must follow business rules and operate within an organization's own environment, and it achieved the highest performance in the benchmark test through features like task decomposition, verification before execution, and automatic reflection.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
OpenAI's upcoming chat-and-work merger in ChatGPT signals the end of all-you-can-prompt pricing
OpenAI combines the Chat and Work modes into a single interface. Starting in December, Plus, Pro, and Business plans will share a common, token-based quota for ChatGPT and Codex. More complex models consume more of this quota, while simple instant chats do not count toward it. In practice, this is likely to result in a decline in ChatGPT’s quality for heavy users on lower-cost plans. The article OpenAI's upcoming chat-and-work merger in ChatGPT signals the end of all-you-can-prompt
Also reported by TechCrunch
Anthropic is working on a system to prove AI models’ identity
Called FlashProve, the system would let anyone check that an AI response really came from the model it claims to be from.
An AI Agent Injected Drugs Into a Live Mouse’s Brain
A biotech startup let an agent choose a gene therapy and successfully inject the treatment, offering a startling glimpse of the future of research labs.
Also reported by The Decoder
Apple starts giving Siri AI access to third-party apps
Apple will now let Siri AI perform actions across third-party apps. As part of the iOS 27.3 update rolling out on Tuesday, Apple announced developers can now integrate Siri AI's new features in "all apps," allowing the voice assistant to draw on a user's personal context, process natural language prompts, and use on-screen awareness to complete requests. The update, which is rolling out as part of a Developer Preview, also adds a new "app skills" feature that third-party develo
OpenAI says ChatGPT is catching up to Google in search
In many circles, "Ask Chat" has replaced "Google it," and that's reflected in a new announcement from OpenAI: the volume of search queries run through ChatGPT now equals 20 percent of the volume run through Google. Adam Fry, OpenAI's consumer product lead for ChatGPT, made the announcement at a press event on Monday. He said the company defines a search as any time a user inputs a query that results in a web search, as opposed to tasks like defining a term or a simple how-to ex
Agentic cheminformatics with Google Antigravity
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.