Results for “agents”

…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…

…Servers out of beta. Modal described human-monitored internal agents generating deployment recipes; automated speculator retraining and distillation remained development directions. By September 17, 2026, endpoint documentation…

…why “skills” may be the minimal viable packaging format for agents, why infra companies have had to reinvent themselves every year, and why application companies have had an easier time surviving model volatility The vertical vs. horizontal…

…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.…

…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…

…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…

…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…

…work connects this approach to cognitive architectures for agents that reason internally, interact with the external world, and learn through those interactions. The closing commentary values Tree of Thoughts as a general framework that…

…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…

…The discussion also anticipates reasoning research influencing agents quickly. Chain of thought and tree of thought are named as promising directions, while ReAct’s adoption in LangChain supplies a concrete example of research moving into…

…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…

…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…