Skip to main content

An open-source ChatGPT rival was just launched by the Stable Diffusion team

The newest challenger to OpenAI’s ChatGPT comes from the company that makes the popular AI image generator Stable Diffusion. Known as StableLM, Stability AI developed this open-source chatbot to democratize access to advanced language models.

Stability AI recently announced the alpha version of StableLM, noting that it is a smaller and more efficient solution than most others. StableLM uses just three billion to seven billion parameters, 2% to 4% the size of ChatGPT’s 175 billion parameter model.

Stability AI's logo appears along with its mascot a stochastic parrot.
Stability AI

Just as Stable Diffusion is a more accessible image generator that can be extended by third-party developers, StableLM offers the same free and open-source solution as an AI chatbot that’s available to all.

Recommended Videos

Thanks to training on a new, experimental data set from EleutherAI called “The Pile,” StableLM can carry on conversations and write code with high performance. Stability AI notes that this data set contains 1.5 trillion tokens, three times larger than the data set used to train most AI models. ChatGPT was trained on”The Pile” but underwent more refinements afterward, including reinforcement learning to help reduce flawed results. ChatGPT has advanced considerably since it was released to the public, and most feel it is the AI chat leader.

A highly efficient AI model is critical to Stability AI since it wants to make StableLM work on lower-cost systems and less powerful GPUs. You can install and run the alpha version of StableLM today. The instructions are in the GitHub repository, along with a notebook with details about using it on a computer with limited GPU capabilities.

The easiest way to try StableLM is by going to the Hugging Face demo page. Since this was just launched and there will likely be high demand, response times could be slow, and as an alpha release, the results won’t be as good as the final release.

For example, when I asked StableLM to help me write an apology letter for breaking someone’s phone, it told me I did what I was supposed to do. The AI somehow misunderstood and thought I gave a gift rather than damaged a phone.

The alpha version of StableLM gets confused sometimes,
Image used with permission by copyright holder

Stability AI includes a disclaimer about the results since StableLM is a pretrained Large Language Model with no additional fine-tuning. It doesn’t use reinforcement learning, as ChatGPT does, so the responses “might be of varying quality and might potentially include offensive language and views.”

It’s unknown whether the upgraded StableLM models that are coming can compete with ChatGPT. At the moment, it is clearly a work in progress. The same was true of another open-source challenger called CollosalGPT.

This isn’t the end of the story, however. Stability AI said larger models with 15 billion, 30 billion, and 65 billion parameters are in progress and should help refine the results. A 175 billion parameter model is planned for the future. Given the limited model size available currently, StableLM is off to a good start.

The open-source nature and the lightweight implementation of the alpha version of StableLM serve the purpose of allowing developers to begin working on applications. There is enough potential for growth and improvement that it’s worth keeping an eye on this new AI chatbot.

Alan Truly
Alan Truly is a Writer at Digital Trends, covering computers, laptops, hardware, software, and accessories that stand out as…
It’s not your imagination — ChatGPT models actually do hallucinate more now
Deep Research option for ChatGPT.

OpenAI released a paper last week detailing various internal tests and findings about its o3 and o4-mini models. The main differences between these newer models and the first versions of ChatGPT we saw in 2023 are their advanced reasoning and multimodal capabilities. o3 and o4-mini can generate images, search the web, automate tasks, remember old conversations, and solve complex problems. However, it seems these improvements have also brought unexpected side effects.

What do the tests say?

Read more
ChatGPT’s awesome Deep Research gets a light version and goes free for all
Deep Research option for ChatGPT.

There’s a lot of AI hype floating around, and it seems every brand wants to cram it into their products. But there are a few remarkably useful tools, as well, though they are pretty expensive. ChatGPT’s Deep Research is one such feature, and it seems OpenAI is finally feeling a bit generous about it. 

The company has created a lightweight version of Deep Research that is powered by its new o4-mini language model. OpenAI says this variant is “more cost-efficient while preserving high quality.” More importantly, it is available to use for free without any subscription caveat. 

Read more
The original AI model behind ChatGPT will live on in your favorite apps
OpenAI press image

OpenAI has released its GPT‑3.5 Turbo API to developers as of Monday, bringing back to life the base model that powered the ChatGPT chatbot that took the world by storm in 2022. It will now be available for use in several well-known apps and services. The AI brand has indicated that the model comes with several optimizations and will be cheaper for developers to build upon, making the model a more efficient option for features on popular applications, including Snapchat and Instacart. 

Apps supporting GPT‑3.5 Turbo API

Read more