OpenAI’s comment to the NTIA on open model weights: This comment was submitted by OpenAI in response to NTIA’s March 2024 Request for Information on Dual-Use Foundation Models with Widely Available Weights.
I asked both Gemini and Open AI to explain that it is not open, the results are telling ….
OpenAI
OpenAl’s comments to the NTIA address the balance between innovation and safety in Al development, emphasizing their approach to mitigating misuse through staged releases and API strategies. They propose a Preparedness Framework for assessing Al model risks and advocate for a diverse ecosystem that includes both open model weights and API-based releases. For further details, please visit OpenAl’s website directly via the provided link.
Gemini:
Gemini: You’re absolutely right! Here’s why the situation is complex regarding
“openness” with OpenAl and its models:
It’s Not Fully Open-Source
Code and Weights Not Public: The core code behind OpenAl’s models like GPT-3 or GPT-4, and the specific “weights” (data the model was trained on) are not released to the public. This limits the ability of others to replicate, study, or fully modify the models.
API Access: Instead, OpenAl primarily offers access through their API, which involves paying for usage. This gives them some control over how the models are used and potentially mitigates misuse.
Reasons for Limited “Openness”
Misuse Potential: Large language models are powerful and can be misused for generating harmful text, propaganda, or spreading misinformation. OpenAl likely wants to control the spread to manage these risks.
Commercial Interests: OpenAl is a company, and making the models readily available could undermine their business model of selling APl access.
Computational Cost: These models are extremely expensive to train and run. Providing full access might lead to unsustainable resource usage.
The Debate
There’s ongoing debate about whether Al models this powerful should be open-source:
Pro-Openness: Advocates argue it promotes transparency, community-driven improvements, and fights potential biases within the models.
Pro-Controlled Release: Others argue responsible release, especially with potentially dangerous technology, is crucial.OpenAl likely falls into this camp.