Facebook owner Meta said on Friday it was launching a batch of new AI models from its research division, including a “self-learning evaluator” that may offer a path toward less human involvement in the AI development process. .
The release follows Meta’s introduction of the tool in an August article, detailing how it relies on the same “chain of thought” technique used by OpenAI’s recently released o1 models to get it to make reliable judgments about the responses of the models.
That technique involves breaking down complex problems into smaller logical steps and appears to improve the accuracy of answers to challenging problems in subjects such as science, coding and mathematics.
Meta researchers used fully AI-generated data to train the evaluator model, also eliminating human input at that stage.
The ability to use AI to evaluate it reliably offers insight into a possible path toward building autonomous AI agents that can learn from their own mistakes, two of the Meta researchers behind the project told Reuters.
Many in the AI field envision these agents as digital assistants intelligent enough to carry out a wide range of tasks without human intervention.
Self-improving models could eliminate the need for an often costly and inefficient process used today called reinforcement learning from human feedback, which requires the involvement of human annotators who must have specialized expertise to label the data. accurately and check that they answer complex math and writing queries. They are correct.
“We hope that as AI becomes more and more superhuman, it will become better and better at checking its work, so that it is actually better than the average human,” said Jason Weston, one of the researchers.
“The idea of being self-taught and able to self-assess is basically crucial to the idea of getting to this kind of superhuman level of AI,” he said.
Other companies included Google and Anthropic have also published research on the concept of RLAIF, or reinforcement learning from AI feedback. However, unlike Meta, those companies tend not to release their models for public use.
Other AI tools released by Meta on Friday included an update to the company’s image identification Segment Anything model, a tool that speeds up LLM response generation times, and data sets that can be used to aid in the discovery of new inorganic materials.
Disclaimer:
The information contained in this post is for general information purposes only. We make no representations or warranties of any kind, express or implied, about the completeness, accuracy, reliability, suitability or availability with respect to the website or the information, products, services, or related graphics contained on the post for any purpose.
We respect the intellectual property rights of content creators. If you are the owner of any material featured on our website and have concerns about its use, please contact us. We are committed to addressing any copyright issues promptly and will remove any material within 2 days of receiving a request from the rightful owner.