Posts
Creating evaluators from a dataset
Why and how to create an evaluator from a datasetRead More →
Building (+ evaluating) a multi-agent e-commerce bot, powered by Stripe
Exploring Stripes new agentic toolsRead More →
Agentic Evaluations for RAG pipelines
Get E2E coverage, holistic evaluations, closer to human evaluatorsRead More →
User feedback driven LLM development
Incorporating user feedback into your LLM analyticsRead More →
Why you may need a family of evaluators
A look at how production-level LLM systems are monitored and trackedRead More →
A practical guide to building custom evaluations
A complete guide on building and managing systems of evaluatorsRead More →
Evals by use case - text to sql to insights
How do I monitor and observe my text to sql LLM applications?Read More →
How evaluations will fit into your future LLMOps stack
For teams looking to experiment with LLMs, and starting looking ahead to their LLMOps stackRead More →
Data-Maxxing in LLMops - how to get more out of your observability layer
For teams looking to experiment with LLMs, and starting looking ahead to their LLMOps stackRead More →
Prototype to Production: an evals-driven approach to building reliable systems
An analytical approach to building reliable LLM systemsRead More →
Turning human in the loop into your own custom evaluation models
An approach to automating your human in the loop evaluationsRead More →
Building + Evals for Multi-Agent Systems (Insired by Swarm by OpenAI)
How to build and evaluate multi-agent systemsRead More →
Custom Multi-Modal Evaluations
A novel approach to custom evaluations for LLMsRead More →
Using lytix to observe lytix
Dogfooding at its finestRead More →
Cloudflare's AI Marketplace
Quick dive into Cloudflare's AI MarketplaceRead More →
September 2024 - Feature Recap 🚢
Recent Features Pushed To lytixRead More →
Pushing the Boundaries of Web Animations with Cursor [Satire]
A humorous look at how far we've come with AI and animations.Read More →
Multimodal LLMs vs. Diffusion modals - what's the difference?
Both create images and video from just text. What makes them different, and what does that mean?Read More →
Cookbook 🧑🍳 in-code guardrails and validators on your inference calls
Follow along to learn how to add guardrails to your workflowsRead More →
Easily configure guardrails and model chains with Optimodel v2!
Developer tools to get foundational models to work for your productRead More →
Google, OpenAI, and the Open Source Problem
Google looks at the open source's contributions to AIRead More →
How Apple’s AI strategy is classic APPL
What Apple Intelligence means for Apple's AI strategyRead More →
Windows 🖥️, Android 📱... Llama 🦙
What Meta's Llama 3.1 drop says about it's AIA strategyRead More →
How SearchGPT could change the internet economy
How SearchGPT could change the internet economyRead More →
Computer Vision + LLMs = AI powered personal trainer?
Building a realtime checker for gym techniqueRead More →
Handling Hallucinations - and other LLM error cases
Deep dive into handling hallucinations and other error cases with LLMsRead More →
What’s the difference between LLM API Providers?
Diving into differences between LLM API Providers.Read More →
Guaranteed Cheapest LLM Calls With No Vendor Lock-In
Building a smart framework to get the cheapest LLM calls possible while still being able to leverage the latest models and features.Read More →
Interactive and Personalized YC Interview Bot
Building a YC interview bot that caters to your specific pitchRead More →
Cost Of Self Hosting Llama-3 8B-Instruct
Sharing my experience attempting to self host Llama-3 8B-InstructRead More →