Results for “agents”

…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…

…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…

…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…

…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…

…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,…

…as the real moat: Replit’s CEO argues that for long-horizon agents, execution + storage + computer use + tools (“agent habitats”) matter as much as the model—positioning the Manus acquisition as an early sign. Replit cites their own…

…and MCP by Anthropic. Integration of Gemini 2.0 with OpenAI Agents SDK: @_philschmid announced a one-line code change to use Gemini 2.0 with the OpenAI Agents SDK. LangChain's Long-Term Agentic Memory Course: @LangChainAI and…

…for local LlamaAgents development/deployments; turnkey document agents template and private-preview hosting for doc-centric workflows (@llama_index, @jerryjliu0). Top tweets (by engagement) “hahahaha the bed sends 16gb of data a month oh…

…support available via Langtrace. Exploring DSPy ReAct Agents for RAG: Members inquired about examples of using DSPy ReAct agents, especially in conjunction with a LlamaIndex retriever for ReAct RAG implementations. Other users pointed to…

…Unsloth notebooks (Unsloth), MLX support (MLX example). Agents: “Skills” standardization, harness UX, and long-running infra realities Agent Skills becoming a de facto portability layer: Anthropic’s “Skills” concept continues to propagate…

…Members discussed how to pass user and system messages to ReAct agents, emphasizing the need for proper classes and formatting tools. The ReActChatFormatter class is essential for structuring chat history appropriately. Clarifying message…

…both ranked 27th'—a reference to recent papers benchmarking AI agents' math problem abilities against the IMO. The actual table, however, only shows human rankings; the implication is a commentary on AI progress in math. While the top…