Guide to Evaluating Large Language Models: Metrics and Best Practices
A model is only as good as the metrics used to evaluate it. Large Language Models (LLMs) have transformed AI with their
Swarm: The Agentic Framework from OpenAI
OpenAI recently made an unexpected move by unveiling Swarm, an experimental and lightweight framework designed to simplify the creation of multi-agent workflows.
OpenAI o1-preview: A Detailed Analysis
OpenAI finally broke the silence and released the much-anticipated “o1-preview.” And there’s a lot to unpack. As an AI start-up whose bread
Building Devin-like SWE Agents using Composio and OpenAI
In March, Cognition Labs’ announcement of Devin—the software engineering agent—caught the eye of developers, founders, and investors alike. The idea of automating
Function Calling Optimizations (GPT4 vs Opus vs Haiku vs Sonnet)
Code: https://github.com/SamparkAI/Composio-Function-Calling-Benchmark/. New: Checkout updated model scores with GPT-4o In the last blog, we introduced the ClickUp function calling benchmark and experimented
Improving GPT 4 Function Calling Accuracy
Join our Discord Community and check out what we’re building! We just published Part 2 of the blog comparing gpt-4-turbo vs opus