🚀 Zaprep: Your Socials on Steroids. Start free with 1,000 automated DMs/month.

Submit your Tool

10,000+ AI tools already listed
10K+Tools
190K+/moViews
70K+/moVisitors
Sign in

AI NewsOpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

9:39 PM IST · August 25, 2026

OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

At the Hot Chips conference on Tuesday, OpenAI shareda more detailed look at Jalapeño, including the first batch of benchmark results for the new system. Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the-art inference processors. “The bottom line is that the results show a very, very significant performance advance over state of the art,” said Richard Ho, OpenAI’s head of hardware, in a press call. “Jalapeño can serve more AI work per unit of power, while also returning responses more quickly. It’s very efficient to serve a lot of customers, but it can also be very low latency.” Notably, that comparison is against an Nvidia Blackwell system — but by the time Jalapeño reaches full deployment, the competition may have advanced significantly. Ho estimated that Jalapeño would deploy at the end of 2026 “in very small volumes,” with more significant deployment coming in 2027. First announced last October, Jalapeño was developed by OpenAI in close collaboration with Broadcom, with OpenAI’s own models assisting in the development process. The company plans to make Jalapeño a multigenerational platform, allowing AI products, models, chips, and memory all developed in concert. Because of that full-stack approach, OpenAI was able to address specific phases in the inference process that often cause friction during inference processing. In particular, Jalapeño is designed to minimize delays during the prefill and communication phases of processing, which OpenAI says often act as bottlenecks. “We designed Jalapeño to minimize data movement and communication delays,” the company said in a blog post presenting the results. “This means that model state, including the KV cache used while generating a response, can be explicitly placed and kept local while the system activates the right combination of compute, memory, and networking for each inference phase.”

read more

Latest AI News

View All News →
Accel-backed Keenable is indexing the web for AI agents

Accel-backed Keenable is indexing the web for AI agents

Search engines were built and optimized for people, who can’t spare the time or attention required to scan entire webpages. But as people increasingly use AI chatbots to search the web and do tasks, there’s a line of thinking that the Internet’s current infrastructure needs to be updated to cater to AI instead, as these bots can read and process much larger portions of information. Andrey Styskin, who previously led Russian search giant Yandex’s search, AI and cloud division, and German AI scientist Matthias Petri are working to solve that problem with their new startup,Keenable. The company recently came out of stealth $26 million in seed funding. Accel led the funding round, which also saw participation from Conviction Partners and some business angels. From Styskin’s perspective, AI chatbots tend to do much better if they canground their responseswith source documents. “This actually creates a new flywheel that is different from what Google learned from human behavior,” he told TechCrunch. Keenable says it has been building a web search index of more than 100 billion documents, and its API is already used in production at several AI labs and inference providers during both training and runtime. The startup wouldn’t disclose who its customers are, but it recently struck apartnership with voice AI company Gradiumto support live information retrieval. Drawing from his experience of 20 years building search at Yandex and Amazon, Styskin explained how Keenable’s product is different from enterprise search solutions that can break down and prove very costly at web scale. “If you do not fine-tune your index structures for a specific task, the cost of serving and scanning the whole internet is enormous because of the volume. That’s why you need to innovate on how you can narrow the search space based on your query very fast. This is what we are bringing to the table,” he said. According to Accel partner Zhenya Loginov, who led the investment, AI players have very few options when it comes to web-scale search infrastructure, especially with Google and Microsoft taking steps toshut downtheirexisting search APIsto avoid cannibalization. Instead, the tech giants are opting for a more bundled approach, and being selective about their partners. To Styskin, these decisions confirmed the opportunity he saw when he was at Amazon, working with Petri on web search infrastructure for AI applications such as Alexa. He’d seenCloudflare datathat AI crawlers were responsible for a growing share of search volume, and started realizing that there was an opportunity to develop web search infrastructure that is built with AI in mind. Armed with that experience, Styskin tapped into his network to hire a handful of former colleagues for his new startup, which is also building proprietary retrieval capabilities. This includes an upcoming product, Web Query Language, which would help AI systems answer questions by combining information from various web sources, even when none contain the full answer. Costs will be an important part of the equation. Styskin says while it is “extremely hard” to convince people to move away from Google for search, theinnovators’ dilemmameans that the U.S. giant is potentially “beatable” on agentic queries, and a smaller company like Keenable can innovate and offer a more cost-efficient solution to AI companies. Still, the costs of building a giant search index are real. “Don’t ask — it is painfully expensive,” he said. But, he says the startup is doing its best to keep costs in check and pace itself. With a team of 15 engineering staff across the U.S. and Europe, the company plans to use the fresh cash to double its headcount by the end of the year to build its go-to-market motion. There are many more steps before the startup can achieve its dream of becoming “the next Google for AI agents.” Other players have entered the space, such asBraveandExa; and Google itself is overhauling its search experience for the AI era. But this broader motion indicates that Keenable’s conviction is also shared at the Googleplex: whether it’s for humans or for agents,the era of the “ten blue links” may be coming to a close.

1 hour ago

View

OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

At the Hot Chips conference on Tuesday, OpenAI shareda more detailed look at Jalapeño, including the first batch of benchmark results for the new system. Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the-art inference processors. “The bottom line is that the results show a very, very significant performance advance over state of the art,” said Richard Ho, OpenAI’s head of hardware, in a press call. “Jalapeño can serve more AI work per unit of power, while also returning responses more quickly. It’s very efficient to serve a lot of customers, but it can also be very low latency.” Notably, that comparison is against an Nvidia Blackwell system — but by the time Jalapeño reaches full deployment, the competition may have advanced significantly. Ho estimated that Jalapeño would deploy at the end of 2026 “in very small volumes,” with more significant deployment coming in 2027. First announced last October, Jalapeño was developed by OpenAI in close collaboration with Broadcom, with OpenAI’s own models assisting in the development process. The company plans to make Jalapeño a multigenerational platform, allowing AI products, models, chips, and memory all developed in concert. Because of that full-stack approach, OpenAI was able to address specific phases in the inference process that often cause friction during inference processing. In particular, Jalapeño is designed to minimize delays during the prefill and communication phases of processing, which OpenAI says often act as bottlenecks. “We designed Jalapeño to minimize data movement and communication delays,” the company said in a blog post presenting the results. “This means that model state, including the KV cache used while generating a response, can be explicitly placed and kept local while the system activates the right combination of compute, memory, and networking for each inference phase.”

1 hour ago

View

Gamma acquires Accel-backed design startup Lica

Gamma acquires Accel-backed design startup Lica

Presentation startupGammahas acquired Accel-backed design startupLicain a bid to build out its own design research lab, TechCrunch has exclusively learned. Lica’s co-founders will lead the effort. Lica started off as an app that could turn screenshots and recordings into project presentations and videos. Founded by Priyaa Kalyanaraman and Purvanshi Mehta in 2023, the company a year later raised $4 million from investors including Accel, South Park Commons, and Village Global. Over the past couple of years, it has focused on working with e-commerce sites to create marketing videos that adhere to brand guidelines. Kalyanaraman said Lica wanted to build AI models around communication methods, including video and design, and the founders were familiar with Gamma’s CEO, Lee Grant, as both companies are backed by Accel and South Park Commons. Those conversations eventually led to the acquisition. “We have a very similar North Star vision of wanting to make visual communication easy. We focused a lot on frontier research and making sure that became accessible to users. But that’s just one part of the solution. Gamma had focused a lot on building distribution, taking the application to 100 million-plus users. Given how fast things are moving, we decided to join forces,” Kalyanaraman told TechCrunch. Gamma will continue to focus on helping people build presentations, but like other design companies, it’s also started offering image generation. The company says it now wants to explore different formats of communication with the new research division. “Presentations for us are today a core use case, but how do we expand what presentations look and feel like, and how do people engage with them in the future? What visuals are possible? How interactive are they? These [questions] all require us to think deeply about the core responsibility of communication. This is why we’re excited to invest in this area, because we don’t think anybody else is thinking at that level,” Lee said. Lica’s Mehta said the new research division would work on customizing the presentation and communication styles of AI models for different audiences and tastes. “The point of the presentation is to communicate a large goal. We are thinking about building a platform where these two goals can be personalized to such an extent that you just get a really good output, and then you’re able to edit for different audiences,” she said. Gamma didn’t reveal what products it plans to build as a result of this acquisition, but it did say that it wants to create fluid, multimodal presentations and other communication modalities. AI presentation startups have received tons of investor attention and money over the last few years. Prezent raised$50 million in two rounds; Gamma raised$68 million at a $2.1 billion valuation; andPresentations.ai was also backed by Accel. We’re even starting to see some consolidation in this category: Earlier this month,OpenAI acquired NextSlide.

1 hour ago

View

Why India’s IT Giants Need Mexico When AI Shrinks the Team

Why India’s IT Giants Need Mexico When AI Shrinks the Team

Indian IT services firms are using Mexico for customer-facing work as AI reshapes global engineering and delivery.

1 hour ago

View

Submit your Tool

Submit AI Tools – The ultimate platform to discover, submit, and explore the best AI tools across various categories.Listed on codetrendy.comFeatured on ListBulb

PoweredByAI.app is an AI Tools Directory helping individuals, businesses, and creators discover the best AI tools for writing, coding, design, productivity, and more.

ContactPromoteAnalyticsTerms of ServiceRefund PolicyPrivacy Policy

© 2026 , Product of011BQ. All rights reserved.