Are you referring to this? https://openai.com/blog/chatgpt-plugins Rabbit's approach is one-sided (train their model to generate needed API calls, and maybe also perform Selenium-style simulated actions?) which should make it more flexible if inherently less reliable than dedicated plugins written by developers from the apps looking to be called via AI. - Source: Hacker News / 2 months ago

To enable the plugin, simply navigate to your settings and locate the "Beta Features" section. There, you'll find the option to activate the ChatGPT code interpreter plugin and unlock its powerful capabilities. - Source: dev.to / 8 months ago

The output from an AI model in response to a prompt is typically textual. To translate these "ideas" into actionable outcomes, AI services need to call APIs. These APIs can initiate actions in the real or digital world, such as making payments, booking an appointment, sending messages, or adjusting room temperatures. In essence, APIs act as the hands of an AI service, enabling it to interact with its environment.... - Source: dev.to / 9 months ago

ChatGPT is an AI language model developed by OpenAI, known for its ability to generate human-like text based on input prompts. It is widely used for various applications, including chatbots, content generation, and data analysis. ChatGPT can access and parse information from websites through plugins and OpenAIs web crawler, making it essential for website owners who don't want their data trained on by AI models to... - Source: dev.to / 10 months ago

As you can see, you get the expected output and this is quite simple to achieve since ChatGPT is context-aware now. However, the issue with this method is that the model’s context is restricted (gpt-4 maximum text length is 8,192 tokens). This strategy will quickly become problematic when input data is huge you may expect thousands of items discovered in sales and you can not provide this large amount of data as... - Source: dev.to / 10 months ago

- Conversational simulation is an emerging idea building on top of model-graded eval” - AI Startup Founder Things to consider when comparing options: “Types of metrics supported (only NLP metrics, model-graded evals, or both), level of customizability; supports component eval (i.e. Single prompts) or pipeline evals (i.e. Testing the entire pipeline, all the way from retrieval to post-processing)” “+method of... - Source: Hacker News / 10 months ago

Humanloop (YC S20) | London (or remote) | https://humanloop.com We're looking for exceptional engineers that can work at varying levels of the stack (frontend, backend, infra), who are customer obsessed and thoughtful about product (we think you have to be -- our customers are "living in the future" and we're building what's needed). Our stack is primarily Typescript, Python, GPT-3. Please apply at... - Source: Hacker News / over 1 year ago

https://humanloop.com/ Find the prompts users love and fine-tune custom models for higher performance at lower cost. - Source: Hacker News / over 1 year ago