OpenAI has unveiled its first custom AI chip, Jalapeño, developed in partnership with Broadcom. This chip is designed specifically for large language model inference and is expected to deliver substantially better performance per watt compared to existing state-of-the-art accelerators. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
Google is also making strides in AI, with an engineer claiming he was fired after creating a command-line interface (CLI) tool for Google Workspace that went viral. The tool, called 'gws', provides unified access to Google Drive, Gmail, Calendar, and other Workspace APIs.
NVIDIA and Scale AI are not mentioned in recent news, but other companies are leveraging AI in various ways. For instance, researchers are exploring the potential of AI in healthcare, particularly in mental health support. A study led by Ruishan Liu evaluated how leading AI models respond to real mental health questions, highlighting both the promise and limitations of AI in this area.
Key Takeaways
['OpenAI has introduced Jalapeño, its first custom AI chip, developed with Broadcom for large language model inference.', 'Jalapeño is expected to deliver substantially better performance per watt than existing state-of-the-art accelerators.', 'The development of Jalapeño took only nine months, a fast pace in the industry.', 'A Google engineer claims he was fired after creating a viral command-line interface (CLI) tool for Google Workspace.', "Researchers are exploring AI's potential in healthcare, particularly in mental health support.", 'Big AI labs are increasingly hiring philosophers to tackle complex problems related to AI development.', 'Washington state is considering legislation to address AI accountability in high-stakes decision-making processes.', 'States should play an active role in shaping the future of AI, ensuring it benefits all citizens while addressing concerns.']OpenAI and Broadcom unveil custom AI chip
OpenAI and Broadcom have introduced Jalapeño, a custom AI chip designed for higher performance and efficiency. This chip is part of OpenAI's strategy to build its full-stack infrastructure for AI. Jalapeño is designed specifically for large language model inference and is expected to offer substantially better performance per watt compared to existing state-of-the-art accelerators.
OpenAI distances itself from Nvidia with in-house AI chip
OpenAI has unveiled Jalapeño, its first custom-designed inference processor, developed in collaboration with Broadcom. This chip is designed to optimize LLM inference and marks a significant step in OpenAI's ambition to build out its entire infrastructure stack. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
OpenAI makes custom AI chip debut with Jalapeño
OpenAI has introduced Jalapeño, a custom AI chip developed in partnership with Broadcom. This chip is designed specifically for AI inference and is part of OpenAI's strategy to reduce dependence on third-party suppliers. Early testing suggests that Jalapeño delivers substantially improved performance per watt compared with existing AI hardware.
OpenAI and Broadcom unveil LLM-optimized inference chip
OpenAI and Broadcom have unveiled Jalapeño, a custom AI accelerator designed for large language model inference. This chip is part of a multi-generation compute platform aimed at making advanced AI faster, more reliable, and more accessible. Early testing shows that Jalapeño will deliver performance per watt substantially better than current state-of-the-art.
OpenAI designed and built its first AI chip named Jalapeño
OpenAI has unveiled Jalapeño, its first custom AI chip, developed in partnership with Broadcom. This chip is designed specifically for LLM inference and was conceived from scratch by OpenAI's engineering teams. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
OpenAI unveils custom chip it designed with Broadcom
OpenAI has introduced Jalapeño, a custom AI chip designed in conjunction with Broadcom. This chip is aimed at AI inference tasks and is expected to deliver performance per watt substantially better than current state-of-the-art accelerators. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
OpenAI unveils powerful Jalapeño AI chip with Broadcom
OpenAI and Broadcom have unveiled Jalapeño, a custom AI chip designed for large language model inference. This chip is part of OpenAI's strategy to build its own AI infrastructure and reduce reliance on external hardware providers. Early testing suggests that Jalapeño delivers better performance per watt than current leading AI accelerators.
OpenAI unveils AI chip Jalapeno
OpenAI has introduced Jalapeño, a custom AI chip co-developed with Broadcom. This chip is designed specifically for AI inference and is expected to deliver performance per watt substantially better than current state-of-the-art accelerators. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
OpenAI reveals its first AI processor: Jalapeño
OpenAI has unveiled Jalapeño, its first custom AI chip, developed in partnership with Broadcom. This chip is designed specifically for AI inference and is expected to deliver performance per watt substantially better than current state-of-the-art accelerators. The development of Jalapeño took only nine months, which is considered a fast pace in the industry.
OpenAI’s Jalapeño Chip Turns The AI Race Into A Hardware War
OpenAI has introduced Jalapeño, its first custom AI chip, developed in partnership with Broadcom. This chip is designed specifically for large language model workloads and is expected to deliver performance per watt substantially better than current state-of-the-art accelerators.
Forescout Emphasizes AI-Driven Security with Forescout Vistaro Platform Rename
Forescout has renamed its Forescout 4D Platform to the Forescout Vistaro platform, reflecting its AI-driven approach to cybersecurity. This platform provides comprehensive visibility and control across managed and unmanaged cyber-physical assets, enabling organizations to better understand and secure complex environments at scale.
Google Engineer Says He Was Fired For Creating The Google Workspace CLI
A Google engineer claims he was fired after creating a command-line interface (CLI) tool for Google Workspace that went viral. The tool, called 'gws', provides unified access to Google Drive, Gmail, Calendar, and other Workspace APIs.
Can AI be your therapist?: Q&A with USC Viterbi’s Ruishan Liu
Researchers are exploring the potential of AI in healthcare, particularly in mental health support. A study led by Ruishan Liu evaluated how leading AI models respond to real mental health questions, highlighting both the promise and limitations of AI in this area.
Bridging potential: how AI training empowers international talents in Taiwan's semiconductor industry
Taiwan's semiconductor industry is leveraging AI training to empower international talents. The Industrial Development Administration has launched a program to provide comprehensive training and support for international talents in key semiconductor technologies.
Google and MediaTek Team Up on 'Triggerfish' AI Chip
Researchers are working to understand what rapidly evolving AI systems can do when it comes to human health and well-being. (Image/Pixabay) Health # Can AI be your therapist?: Q&A with USC Viterbi’s Ruishan Liu The researcher is building evaluation methods for AI in healthcare. Her latest project asked 100 mental healt...
Webinar Today: Modern Exposure Validation in the AI Era
A webinar today will discuss modern exposure validation in the AI era, focusing on how AI turns vulnerabilities into exploits quickly and how to validate exposures effectively.
Why big AI labs are hiring so many philosophers
Big AI labs are increasingly hiring philosophers to tackle complex problems related to AI development, such as ensuring AI systems are aligned with human values and addressing potential risks.
What if AI rejects you for housing or healthcare? WA needs a law
Washington state is considering legislation to address AI accountability, particularly in high-stakes decision-making processes such as housing, healthcare, and employment.
States should not be sidelined on artificial intelligence
States should play an active role in shaping the future of AI, ensuring it is developed and deployed in ways that benefit all citizens while addressing legitimate concerns about privacy, consumer protection, and job displacement.
Sources
- OpenAI Unveils Custom AI Chip
- OpenAI Distances Itself From Nvidia With Jalapeño, Its First In-House AI Chip
- OpenAI Makes Custom AI Chip Debut With Jalapeño As Part of Broadcom Deal
- OpenAI and Broadcom unveil LLM-optimized inference chip
- OpenAI Has Designed And Built Its First AI Chip Named Jalapeño In Partnership With Broadcom
- OpenAI unveils custom chip it designed with Broadcom to boost its AI infrastructure
- OpenAI Unveils Powerful Jalapeño AI Chip With Broadcom
- OpenAI unveils AI chip Jalapeno
- OpenAI reveals its first AI processor: Jalapeño
- OpenAI’s Jalapeño Chip Turns The AI Race Into A Hardware War
- Forescout Emphasizes AI-Driven Security with Forescout Vistaro™ Platform Rename
- Google Engineer Says He Was Fired For Creating The Google Workspace CLI
- Can AI be your therapist?: Q&A with USC Viterbi’s Ruishan Liu
- Bridging potential: how AI training empowers international talents in Taiwan's semiconductor industry.
- Google and MediaTek Team Up on 'Triggerfish' AI Chip to Supercharge Agentic Hardware
- Webinar Today: Modern Exposure Validation in the AI Era
- Why big AI labs are hiring so many philosophers
- What if AI rejects you for housing or healthcare? WA needs a law
- States should not be sidelined on artificial intelligence
Comments
Please log in to post a comment.