Humanloop is now generally available!

After 2 years of working closely with early customers, we're opening access to our full evals platform.

🧵 Here's what we've learned and how we can help you build great AI products: When we started, ChatGPT didn't exist. GPT-3 was cutting-edge and there was no developer tooling.

We had the privilege of supporting pioneering teams at @duolingo, @gustohq, @TrustVanta and many others on their journey from 0 → 1.

We worked closely together to understand the challenges of building with LLMs and define the standards for AI engineering.

What did we learn?

Prompt Engineering is a thing.

Here's Prompt Engineering 101 for working with LLMs like GPT-3 1. Just ask

With the advent of instruction-tuned models, these models are usable without needing to get clever about it. If in doubt, just ask.

The playground may be the first way you interact with GPT-3... but it's also an IDE in disguise.

We want to transform it to be best way to build useful apps with LLMs. Here's how ↓ Prompt templates

Put in an {{input}} and you can separate variables from the boilerplate. Making it far easier to try out new ways of prompting.

Today we're excited to announce that we're partnering with @CarperAI of Stability on bringing the first RLHF-trained GPT-3 like model to the open source community.

This will be huge. Let us explain RLHF – Reinforcement Learning from Human Preferences.

Models are fine tuned using RL from human feedback. They become more helpful, less harmful and they show a huge leap in performance. An RLHF model was preferred over a 100x larger base GPT-3 model.