Results for “agents”

…Generation (RAG) in the development of advanced AI agents. Limitations of LlamaIndex with function calls: Discussion revealed that LlamaIndex does not support function calls with the current API configuration, hindering tool usage. Members …

…pages for both 1.8B and 20B versions. Theme 2. Advanced AI Agents with Desktop Control Giving Llama its own Windows instance (Score: 52, Comments: 24): LLaMA, a large language model, was given control over a Windows instance with access to …

…Speculative Decoding, vLLM scaling, and kernel-generation agentsSpeculative Speculative Decoding (SSD): Tanishq Kumar introduces SSD, claiming up to 2× faster than leading inference engines (vLLM, SGLang), collaborating with Tri Dao and…

…OpenAI's CriticGPT Release Stable Release of Embodied Agents Toolkit Open Source OCR for Kazakh Language Blog on Reinforcement Learning Specialization Zero-Shot Generating Spatial Sound from Images OpenAI Unveils CriticGPT: A user shared a …

…focused on ARC-AGI-3’s efficiency-based scoring, which compares agents against the second-best human action count and heavily penalizes extra steps. @scaling01 argued this makes the headline “<1%” difficult to compare with prior ARC…

…along with tutorials on building AI apps and plan-and-execute agents. Photonics and NVIDIA Advances: Discussions around a new photonics chip that's 1000x faster than traditional chips and NVIDIA's H100 GPU paired with ARM-based CPUs drawing…

…as a major jump in software engineering and long-horizon agents, citing SWE-bench Pro 57.2, Claw-Eval 63.8, and τ3-Bench 72.9, with claims of 1,000+ autonomous tool calls. The non-Pro model adds native omnimodality and a 1M-token context…

…memorization in LLMs, and a tree search algorithm for LM agents to improve inference-time exploration.

…models, post-transformers, synthetic data, smol models, and agents. Twitter recaps feature proposals for benchmarks measuring LLM calibration and confidence in falsehoods, and the debut of QVQ outperforming GPT-4o and Claude 3.5 Sonnet.…

…level, “our highest-capability setting, coordinating multiple agents across parallel workstreams to finish complex tasks faster”:max gives GPT‑5.6 even more time than xhigh to reason and explore alternatives, run checks, and revise its…

…it with LangGraph and aiding in the creation of AI research agents. It includes practical debugging and optimization tips, ensuring a smoother implementation experience. LlamaCloud's Financial Data Superpower: In a recent demo, the team…

…play rather than a benchmark-chasing frontier release. Agents, Sandboxes, Memory, and Search Are Becoming the Real Product SurfaceThe stack is shifting from model calls to agent runtimes: Several launches converged on the idea that the main…