Humanloop: LLM evals platform for enterprises

Prompt Engineering 101

In this post, we'll explore the fundamentals of prompt engineering. We'll explain how Large Language Models (LLMs) interpret prompts to generate outputs, and provide tips and tricks to get you started prototyping and implementing LLMs quickly.

Raza Habib

Sinan Ozdemir

Humanloop partners with Stability AI to build the first open-source InstructGPT

We’re excited to be partnering with Stability AI, to build and release the first open-source large language model that can follow human instructions.

Raza Habib

Announcing: Humanloop for Large Language Models

Today we're excited to open up access to Humanloop for all developers who want to build next-generation applications with large language models like GPT-3.

Raza Habib

Coming soon: Humanloop for LLMs

Today, we are announcing the preview of Humanloop for Large Language Models (LLMs). Sign up to be part of the closed beta.

Jordan Burgess

How to Improve GPT‑3 with Human Feedback

Fine-tuning GPT‑3 can make it faster, cheaper and more accurate. Humanloop makes it dramatically easier to do this, while aligning the model with the preferences of your users.

Jordan Burgess

Why you need to calculate error bounds on your test metrics

Machine learning test metrics should always be calculated with credible intervals. Credible intervals give you upper and lower bounds on test performance so you know how big your test needs to be and when to trust your models. Humanloop Active Testing can give you uncertainty bounds on your test metrics and makes this easy.

Raza Habib

What is human-in-the-loop AI?

Human-in-the-loop AI is an automation approach which means you can quickly deploy a working model, with less data and with guaranteed quality predictions. In this post we'll explain what HITL is and how you can make use of this approach in your own AI projects.

Jordan Burgess

Why you should take a data first approach to AI

Machine learning systems are born through the marriage of both code and data. Academia mostly focuses on ways to improve the learning algorithms, the how of machine learning. When you come to build practical AI systems though the dataset you're training on has at least as much impact on performance as the choice of algorithm.

Raza Habib

How good is GPT-3 in practice?

We discuss the real world performance of Open AI's GPT-3 language model and speculate on what the future of large pre-trained language models may hold.

Raza Habib

Four lessons from a year building tools for machine learning

The most surprising lessons about how to build tooling for machine learning, what is needed going forwards and why domain experts will play a much larger role in the future of AI.

Raza Habib