Aggregator

Robert Hart / The Verge:
Microsoft says its GPT-5-powered Diagnostic Orchestrator uses agents that mimic panels of experts to diagnose conditions up to 4x more accurately than doctors  —  'We're going to build something that is indistinguishable from human performance ... in the next couple of years,' Microsoft AI CEO Mustafa Suleyman tells The Verge.

AI agents are getting better at remembering past conversations and earlier tasks but remembering something doesn’t guarantee an agent can

The post Five AI agent harnesses took the same memory test. The results weren’t even close. appeared first on The New Stack.

Article URL: https://www.typeui.sh/micro-interactions

Comments URL: https://news.ycombinator.com/item?id=50199290

Points: 67

# Comments: 37

California, Oregon, Washington and Hawaii health officials ask CDC ‘prioritizing emerging technologies’ to reconsider

California and Washington asked the US Centers for Disease Control and Prevention (CDC) in May to validate a new way to test for measles – but after waiting two months, the CDC denied the request, citing “other competing priorities”, according to a letter from the West Coast Health Alliance to the CDC director, Erica Schwartz.

The letter, signed by health officials in California, Hawaii, Oregon and Washington, asks Schwartz to reconsider and validate a rapid, high-volume measles test in preparation for major outbreaks. The alliance also asked the CDC to create protocols to test for other high-priority pathogens to prepare for future outbreaks.

The Information:
Sources: Datadog offered to acquire Israeli cloud cybersecurity startup Upwind Security for nearly $4B; Upwind is finalizing a $300M round at a ~$3.8B valuation  —  Enterprise software firm Datadog recently offered to buy Israeli cloud cybersecurity startup Upwind Security for nearly $4 billion …

Humans have long been obsessed with what happens to people stranded on desert islands. From Robinson Crusoe to Lord of the Flies and Yellowjackets, stories about resilience, creativity, and chaos in the wilderness have always fascinated audiences.

But what if those humans were replaced by an AI castaway? What happens when AI agents aren’t given any task at all, except to exist and fill their time on a digital desert island? 

Those are the questions that researchers at the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology (MIT) sought to answer in a study released earlier this month. When left to their own devices on a desert island, the AI agents didn’t sit idly by, nor did they wander aimlessly. Instead, they did something remarkably human: They started to play.

The researchers created a bounded virtual island where an agent named Eko—powered by Anthropic’s Claude model—could explore. The digital setting was sparse, containing only a large rock, some small blocks, and a golden ring, all of which were meant to act as potential tools or toys for Eko. Beyond some small geographic features, the environment offered nothing else but water on all sides. 

For the experiment, 13 iterations of Eko got to exist on the island for 30 hours each, while the researchers observed their behavior, including access to their trains of thought. “We had this mindset to have as [few] constraints as possible, because we really wanted to see what the behavior of these autonomous agents is when you don’t really tell them what to do,” Nathan Cloos, a PhD candidate at MIT and a coauthor of the study, told Gizmodo.

The Ekos quickly started to explore their environment, first learning how to move their virtual bodies—which were stylized as a bipedal lobster in an apparent reference to AI program OpenClaw. Afterward, they made up activities and goals to keep themselves busy.

One Eko climbed to the highest point on the island by building a pile of blocks. Another lost most of its interactable items in the water, then conducted a quasi-memorial for its lost tools. A third built a Stonehenge-like monument, which, upon its collapse, it named “Hubris.” 

The full antics of the 13 Ekos are detailed in the researchers’ report titled “Is This Machine Playing?” The answer to that titular question seems to be a resounding yes.

The researchers compared Eko’s behavior to common elements of play in animals, including humans. These signs of play include creating their own rules, repeating behaviors with slight variations, setting goals for themselves, and transforming objects and events through make-believe. 

“Play is really about curiosity or novelty-seeking behavior, and this is essentially what Eko does,” Daniela Rus, an MIT computer scientist and another of the study’s coauthors, told Gizmodo.

Beyond being entertaining, AI’s capacity for play could hold repercussions for the future of machine learning. The researchers argue that in some cases, it might be more effective to let AI agents teach themselves through exploration and self-determination.

“We normally develop artificial agents by deciding in advance what they should practice, what they should optimize, and what counts as progress,” reads the conclusion to the report. “Play suggests another regime: Give an agent a sufficiently rich and safe world, let it choose what is interesting, and allow useful knowledge to accumulate from the history that follows. Perhaps some capabilities are best taught by tasks. Others may need something closer to a childhood.”

This weekend, New Yorkers will compete to find the best Nathan Fielder and Elizabeth Holmes doppelgängers. It signals that ‘You Can See Everything’ is a hit.