# Apps & integrations

Work with all your favourite apps and tools or create your own custom integrations using the Ghost API.

## Work with your existing tools

It's possible to connect your Ghost site to hundreds of the most popular apps and tools using integrations that take no more than a few minutes to setup.

Whether you need to automate workflows, connect your email list, build a community or embed products from your ecommerce store, our integrations library has got it all covered with hundreds of tutorials.

## Zapier

On top of this, you can connect your Ghost site to more than 1,000 external services using the official integration with Zapier.

Zapier sets up automations with Triggers and Actions, which allows you to create and customise a wide range of connected applications.

Example: When someone new subscribes to a newsletter on a Ghost site (Trigger) then the contact information is automatically pushed into MailChimp (Action).

Here are the most popular Ghost<>Zapier automation templates:

## Custom integrations

At the heart of Ghost sits a robust JSON API – designed to create, manage and retrieve content with ease.

It's possible to create custom Ghost integrations with dedicated API keys and webhooks from the Integrations page within Ghost Admin.

Beyond that, the API allows you to build entirely custom publishing apps. You can send content from your favourite desktop editor, build a custom interface for handling editorial workflow or use Ghost as a full headless CMS with a custom front-end.

The Ghost API is thoroughly documented and straightforward to work with for developers of almost any level.

## Final step: Themes

Alright, on to the last post in our welcome-series! If you're curious about creating your own Ghost theme from scratch, find out how that works.

We’re releasing an analysis showing that since 2012 the amount of compute needed to train a neural net to the same performance on ImageNet 1 classification has been decreasing by a factor of 2 every 16 months. Compared to 2012, it now takes 44 times less compute to train a neural network to the level of AlexNet 2 (by contrast, Moore’s Law 3 would yield an 11x cost improvement over this period). Our results suggest that for AI tasks with high levels of recent investment, algorithmic progress has yielded more gains than classical hardware efficiency.

Algorithmic improvement is a key factor driving the advance of AI. It’s important to search for measures that shed light on overall algorithmic progress, even though it’s harder than measuring such trends in compute.

##### 44x less compute required to get to AlexNet performance 7 years later
Total amount of compute in teraflops/s-days used to train to AlexNet level performance. Lowest compute points at any given time shown in blue, all points measured shown in gray.25678910111213141516

## Measuring efficiency

Algorithmic efficiency can be defined as reducing the compute needed to train a specific capability. Efﬁciency is the primary way we measure algorithmic progress on classic computer science problems like sorting. Efficiency gains on traditional problems like sorting are more straightforward to measure than in ML because they have a clearer measure of task difficulty. [1]

However, we can apply the efficiency lens to machine learning by holding performance constant. Efficiency trends can be compared across domains like DNA sequencing17 (10-month doubling), solar energy18 (6-year doubling), and transistor density3 (2-year doubling).

We are standardizing OpenAI’s deep learning framework on PyTorch. In the past, we implemented projects in many frameworks depending on their relative strengths. We’ve now chosen to standardize to make it easier for our team to create and share optimized implementations of our models.

$pip install procgen # install$ python -m procgen.interactive --env-name starpilot # human
\$ python <<EOF # random AI agent
import gym
env = gym.make('procgen:procgen-coinrun-v0')
obs = env.reset()
while True:
obs, rew, done, info = env.step(env.action_space.sample())
env.render()
if done:
break
EOF


### Design principles

We’ve designed all Procgen environments to satisfy the following criteria:

• High Diversity: Environment generation logic is given maximal freedom, subject to basic design constraints. The diversity in the resulting level distributions presents agents with meaningful generalization challenges.

• Fast Evaluation: Environment difficulty is calibrated such that baseline agents make significant progress after training for 200M timesteps. Moreover, the environments are optimized to perform thousands of steps per second on a single CPU core, enabling a fast experimental pipeline.

• Tunable Difficulty: All environments support two well-calibrated difficulty settings: easy and hard. While we report results using the hard difficulty setting, we make the easy difficulty setting available for those with limited access to compute power. Easy environments require approximately an eighth of the resources to train.

• Emphasis on Visual Recognition and Motor Control: In keeping with precedent, environments mimic the style of many Atari and Gym Retro games. Performing well primarily depends on identifying key assets in the observation space and enacting appropriate low level motor responses.

OpenAI builds free software for training,
benchmarking, and experimenting with AI.