AI research and deployment company OpenAI formalizes its new model ‘text-davinci-003’ which adds to the GPT-3 model family and builds on previous InstructGPT models. The latter makes it possible to provide improved behavior in the rendering obtained by querying the AI.
New developments in the field of artificial intelligence
A new addition to the GTP-3 model family has been confirmed by OpenAI. Named ‘text-davinci-003’, this language understanding model makes it possible to bring more precision and quality to the renderings that one wishes to obtain by questioning the AI. In general, training this model produces more “truthful” and less “toxic” results. In order to better respond to research intentions and offer a more refined rendering, InstructGPT models are based on an approach closer to human beings.
The new capabilities offered by ‘text-davinci-003’ make it possible to handle complex instructions, which leads to more creative possibilities in how it can be used.
The main idea behind this addition is to facilitate the creation of longer and more qualitative content. A comparison between the productions made by this model and by the previous version shows a significant evolution in this direction:
For example, to the question: I am trying to write a web application. What backend frameworks can I use, and what are their pros and cons? », the ‘text-davinci-002’ version gives a rendering in text format, summarizing the points to be taken into account, without trying to go into detail. We can see an example below:
There are many backend frameworks that could be used for a web application. Some of the most popular include Django, Ruby on Rails, and Express.js. Each of these frameworks has its own advantages and disadvantages, so it is important to choose one that will meet the specific needs of your application.
On the same question, the new version offers more visibility in the rendering of the answer, as well as more details:
- Django: Django is a popular Python-based web framework. Pros: Django is powerful and well documented, which makes it easy to get started. It also supports a wide range of databases and APIs, allowing you to easily integrate with other services. Cons: Django can be difficult to scale for large applications and can be slow for certain types of requests.
- Ruby on Rails: Ruby on Rails is a popular web framework based on the Ruby programming language. Pros: Ruby on Rails is easy to learn and can be used to build powerful web applications quickly. It also has a wide range of built-in features, such as authentication and authorization. Cons: Ruby on Rails can be slow and resource intensive, and it can be difficult to scale.
To ensure this rendering, OpenAI used reinforcement learning from human feedback (RLHF), which allows for much more convincing results for following instructions compared to GPT-3.
To take advantage of this new version of the OpenAI model, like that of other Davinci language models, it is necessary to use the company’s API at the same price as the other Davinci base language models (0, $0200 / 1000 tokens).