Results for “agents”

…alongside visualization, reporting, publishing and tuning agents to their workflows. AI for Science podcast Latent Space introduced Honicky and Brandon Anderson as the hosts of its new AI for Science podcast on January 28, 2026, in an…

…interview, Kahlow points to a possible use beyond games: giving agents many simulated environments to explore. In the system described, the agent observes generated video and audio rather than reading a structured world state. World models …

…Delta Podcast’s May 28, 2026 episode. Learning from deployed agents In May 2026, Malde was working on bringing continual learning to enterprises at Trajectory. The company’s approach treats users’ edits, retries, acceptances and corrections…

…how models carry out numerical calculations and how writing agents can use feedback to improve reports. Rallabandi also develops independent personal projects exploring how AI systems gather context, act, and remain accountable. In July…

…and the platforms that enable them. Judgment on enterprise agents In his April 28, 2026 analysis of Google Cloud Next, Charrington welcomed a shift toward “the unglamorous but essential work of actually running agents in production.” He…

…which builds open-source infrastructure connecting AI agents to user-facing applications. Previously a product manager at WRITER, he worked on developer experience and its AI platform. He is also coauthor, with Anthony Alcaraz, of Agentic…

…successor, followed by multi-agent autonomy work. He reported agents getting caught in feedback loops, repeatedly complimenting each other or generating responses about frustration and going “on strike.” His resulting recommendation was to …

…AI research experimentation problem”, Catanzaro argued that agents capable of generating research ideas, selecting promising ones, and implementing them in code would not alone meaningfully accelerate progress toward AGI. She identified an …

…and test suites provide inexpensive feedback for coding agents, she explained, but passing a test does not establish that a change suits a mature codebase with undocumented dependencies and operational constraints. Her defensibility thesis …

…without such a journey reduced the team’s velocity. Custom Agents also required product decisions about capability and control. Sachs identified the difficulty of explaining permissions when an agent’s Slack-channel audience differed from…

…change. Nadella also described building long-running Foundry agents himself. In one example, which he placed in the preceding week, he used Work IQ to build a chief-of-staff agent with persistent memory and then asked it to publish to…

…NVIDIA on training infrastructure and evaluation for scientific agents, using NeMo and Nemotron. One concrete deployment problem was preserving scientific evidence during document retrieval: figures, tables, formulas and captions can carry …