# Understanding Your Claude Code Spend: What’s Actually Driving the Cost I’ve been spending time looking at how teams are actually using Claude Code, and one thing keeps coming up: most… [Read](/content/site/blog/claude-code-context-bloat/index.html) --- ## Pretraining: Breaking Down the Modern LLM Training Pipeline LLM training shapes everything from what a model knows to how it reasons and responds. So, understanding how models are… [Read](/content/site/blog/pretraining/index.html) --- ## Major Releases: Auto-Optimize Multi-Step Agents, Annotate & Score Entire Chatbot Convos When multiple steps in an agentic system are contextually related, logging and evaluating individual LLM calls doesn’t tell the whole… [Read](/content/site/blog/comet-product-releases-july2025/index.html) --- ## AI Assisted Coding with Cursor AI and Opik How AI can help you move beyond vibe coding and become an effective AI engineer faster than you think Dear… [Read](/content/site/blog/cursor-vibe-coding/index.html) --- ## Release Highlights: Discover Opik Agent Optimizer, Guardrails, & New Integrations As LLMs power more complex, multi-step agentic systems, the need for precise optimization and control is growing. In case you… [Read](/content/site/blog/comet-product-releases-june2025/index.html) --- ## Announcing Opik’s Guardrails Beta: Moderate LLM Applications in Real-Time We’ve spent the past year building tools that make LLM applications more transparent, measurable, and accountable. Since launching Opik, our… [Read](/content/site/blog/opik-guardrails-release/index.html) --- ## From Observability to Optimization: Announcing the Opik Agent Optimizer Public Beta At Comet, we’re driven by a commitment to advance innovation in AI, particularly in the realm of LLM observability. Our… [Read](/content/site/blog/automated-prompt-engineering/index.html) --- ## Major Releases: MCP Server & Google Agent Dev Kit Support We’ve just rolled out two major updates in Opik, Comet’s open-source LLM evaluation platform, that make it easier than ever… [Read](/content/site/blog/comet-product-releases-april2025-2/index.html) --- ## How Contributing to Open Source Projects Helped Me Build My Dream Career in AI 6 years ago, I decided to open-source my Python code for a personal project I was working on, which led… [Read](/content/site/blog/contributing-to-open-source-ai/index.html) --- ## LLM Evaluation Complexities for Non-Latin Languages Large language models (LLMs) have revolutionized natural language processing, yet most development and evaluation efforts have historically centered around Latin-script… [Read](/content/site/blog/complexities-for-non-latin-languages-llm-evaluations/index.html) --- ## SelfCheckGPT for LLM Evaluation Detecting hallucinations in language models is challenging. There are three general approaches: The problem with many LLM-as-a-Judge techniques is that… [Read](/content/site/blog/selfcheckgpt-for-llm-evaluation/index.html)