Results for “agents”

…research leader working on human data, alignment and coding agents. In a February 23, 2026 interview, she described herself as a VP of research responsible for the Codex, Human Data and Alignment teams. Her Human Data team collaborated with…

…complete account of hallucination in every use case. Evaluating agents through their work For GDPVal AA, Cameron described adapting OpenAI’s GDPVal dataset into an evaluation that could run across models, using a reference agent harness and…

…for support tickets and feeding interventions back into the agents. As of September 20, 2026, YC listed both as active GloGlo founders. GloGlo describes its AI glucose companion as turning continuous glucose data into personalized insights …

…In his April 2026 interview, he explained his preference for agents that critique one another, reproducible experimentation and customer simulations calibrated against historical behavior. Agent critique and the cost of review Parakhin said…

…methods. Their finding was that data diversity could help agents focus on meaningful information without changing the underlying RL method. In the October 25, 2022 paper In-context Reinforcement Learning with Algorithm Distillation, Laskin …

…humans involved in the deployment of increasingly capable agents. She also described ongoing work to detect hallucinations through internal signals of uncertainty or user-pleasing behavior, and to investigate mitigation within the model.…

…agent engineering function and helped build customer-facing AI agents, including a Sonos agent for troubleshooting speaker connections. In July 2026, Latent Space identified her as Sierra’s Head of Agent Engineering, leading a global team…

…Her earlier work at Contextual AI and Unstructured explored how agents select tools and retrieve information, including a concrete decision to combine long-context models with retrieval rather than choose one approach for every extraction…

…and Alessio for a discussion of Code Interpreter, Llama 2, AI agents, companions, and the emerging AI engineer profession. He invited them back for a conversation published in April 2024, examining competition across the AI stack and what…

…did not use CICERO during the tournament. Public views: scaling agents beyond games By June 2025, Brown favored improving general model capabilities over elaborate task-specific scaffolding. Discussing Pokémon evaluations, he preferred…

…a September 2022 public beta. Users could create conversational agents and interact with them. The founders argued that conversation could support tasks requiring clarification, feedback and adaptation to individual needs. At that stage,…

…models on real repository issues, SWE-agent, which gives agents an interface for working with code, and ProgramBench, which tests their ability to rebuild programs from their behavior and documentation. His contributions also include…