Results for “agents”

…also introduced agentic features like restaurant-reservation agents and reduced pricing for Gemini 2.5 Flash. Meta AI unveiled the open-weight Code World Model (CWM) 32B, excelling in code semantics and math benchmarks, with innovations in …

…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 …

…citation quality, and frontier-scale validation. Coding Agents, Harnesses, and Skills InfrastructureOpenAI’s Codex momentum showed up repeatedly: OpenAI Devs promoted a Codex x Notion event, while company posts and leadership commentary…

…and Microsoft Foundry provides managed infrastructure for agents. Microsoft develops its own models alongside its OpenAI partnership, and in January 2025 consolidated developer and AI-platform teams into CoreAI to build its Copilot and AI…

…solutions. Notable discussions included the usage of LLM agents and model customization. GitHub link to microchain example Discussions about fine-tuning methods and tutorials, including the sharing of a Tamil tuned model and a Mistral 7B…

…of language models and AutoGen, a framework for coordinating agents powered by language models, humans and tools. Synthetic data and smaller models Ronen Eldan and Yuanzhi Li’s TinyStories, listed as a May 2023 publication, uses GPT-3.5 and…

…Tooling, and Infrastructure Memory and Conversation History for Agents: Anthropic announced that Claude can now reference past chats to maintain context, a feature @swyx calls instructive for how they solve problems with transparency and…

…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…

…engineering is becoming the main differentiator for coding agents: Several posts converged on the same thesis: the winning stack is now model + harness + eval loop, not just a stronger base model. A long Zhihu summary argued that DeepSeek…

…to advance deployment support. From models to products and agents During the fourth quarter of 2025, MiniMax updated M2, M2.1 and M2-her. M2 emphasized coding, tool use and deep search; M2.1 focused on complex coding and workplace tasks…

…using this tutorial, noting it demonstrates how to build agents with LlamaIndex, starting with a basic example and adding Retrieval-Augmented Generation (RAG) capabilities. The member used BAAI/bge-base-en-v1.5 as their embedding model,…

…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 …