Results for “agents”

…Claude Opus 4.5, a new flagship model excelling in coding, agents, and tooling with a significant 3x price cut compared to Opus 4.1 and improved token efficiency using 76% fewer output tokens. Opus 4.5 achieved a new SOTA on SWE-bench…

…users a declarative interface for specifying pipelines and uses agents to rewrite them. Its design combines logical rewrites tailored to LLM tasks, task-specific validation prompts for evaluating candidate plans, and an optimization…

…makes ordinary weaknesses more expensive for defenders. LLM agents bring a step increase in the number of paths an attacker can test, the speed at which failed paths can be replaced, and the volume of evidence defenders must interpret. What…

…alternative reasoning paths. His work also addresses how agents use software and how to evaluate their reliability. In April 2026, Tencent identified him as its Chief AI Scientist. From OpenAI to Tencent Yao’s personal website, last updated…

…Use: There's a noted 50% increase in token usage when LangChain agents employ tools, attributed to the tools' process of data retrieval and tokenization. While the system prompt is executed once for inference assumptions, not all tools…

Simile AI builds models and agents that simulate human behavior, allowing organizations to test decisions against modeled individuals and populations. Cofounded by Joon Sung Park, Michael Bernstein, Percy Liang and Lainie Yallen, with Park …

…affecting model quality measurement. Discussions on coding agents and developer experience convergence continue in the AI community.

…systems were precisely what they wanted to avoid. Retrieval, agents and focus Eskildsen argues that models can learn to reason about knowledge but still need external systems that preserve it in full fidelity. In the March 12, 2026…

…Building AI-native observability with Logfire, Pydantic AI for agents, and why .ipynb needs to go Latent.Space

…Notion AI prototype with Ivan Zhao to the development of Custom Agents. His work includes redesigning how agents interact with Notion and turning evaluation into a workflow agents can help execute. In an April 2026 interview with Sarah…

…API: @tonic_1 introduced the community to the Transformers Agents API from Hugging Face, noting its experimental nature and outlining the three agent types: HfAgent, LocalAgent, and OpenAiAgent for diverse model use cases. Seeking Clarity…

…the lethal trifecta framework for describing how tool-using agents can expose private information. Datasette and LLM: data tools meet language models Willison announced Datasette’s first public version on November 13, 2017. It exposes…