Blogs
Fireworks f1: A breakthrough in complex reasoning with Compound AI
At Fireworks, we believe the future of AI is shifting to compound AI systems that combine specialized models and tools to achieve better performance, reliability and control, compared to a single model.
BlogsDistillation with Reasoning: Can DeepSeek R1 Teach Better Than Humans?Fireworks
BlogsUnlock Advanced Reasoning with NVIDIA Nemotron Nano 2 Models on FireworksFireworks
BlogsIntroducing Llama 3.1 inference endpoints in partnership with MetaFireworks
BlogsHow Fireworks evaluates quantization precisely and interpretablyFireworks
BlogsFirefunction-v2: Function calling capability on par with GPT4o at 2.5x the speed and 10% of theFireworks
BlogsDeepSeek V4 Pro: Tops SWE-Bench & Cuts Cost per Task by 3x vs. Fable 5Fireworks
LearnModel Types and PerformanceVercel
BlogsHoneycomb Acquires Grit and Expands Leadership Team to Accelerate Customer Value and EnterpriseHoneycomb
BlogsCommand A Reasoning: Control for AI Agents | CohereCohere
BlogsMotherDuck Window FunctionsMotherduck
BlogsRemote agents in Vibe. Powered by Mistral Medium 3.5. | Mistral AIMistral
BlogsWhat Is Observability? Key Components and Best PracticesHoneycomb
ResearchEAGER: Entropy-Aware Generation for Adaptive Inference-Time ScalingCohere
BlogsThe Data Warehouse powered by DuckDB SQLMotherduck
BlogsObservability Where You Work: Introducing the Honeycomb Slackbot in BetaHoneycomb
BlogsTrust at First Prompt: The New Design Challenge of AI InterfacesHoneycomb
ResearchCALIBER: Calibrating confidence before and after reasoning in language modelsCohere
ResourcesHow to turn an object into a JSON string in C#Sentry
LearnMulti-Step & Generative UIVercel
BlogsHow to Build an AI Agent: A Practical GuideCohere
