Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding18m ago Instagram now lets you add tagged photos to your profile grid19m ago Sure, Meta’s AI Muse works, but it sure creeps me out19m ago AI agents are flooding public services with new requests25m ago The iPhone Duo just might live up to the hype26m ago People are flooding X with joke resignation announcements imitating the viral AI extinction warning28m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities36m ago Antioch raises $32m to test robots in simulation before they touch hardware44m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit59m ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago

Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding18m ago Instagram now lets you add tagged photos to your profile grid19m ago Sure, Meta’s AI Muse works, but it sure creeps me out19m ago AI agents are flooding public services with new requests25m ago The iPhone Duo just might live up to the hype26m ago People are flooding X with joke resignation announcements imitating the viral AI extinction warning28m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities36m ago Antioch raises $32m to test robots in simulation before they touch hardware44m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit59m ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago

Chips & Compute AI Research2 min reading time

OpenAI says its Jalapeño chip can power faster AI responses than the competition

Covered by 4 sourcesPublished 16 days ago

OpenAI introduced its Jalapeño AI chip, designed with Broadcom, which delivers faster AI inference and greater efficiency than Nvidia's top superchips. Benchmarks show Jalapeño offers 1.5-1.9x more AI work per watt and 1.7-3.6x lower latency across multiple models. OpenAI plans limited deployment by end of 2026 and increased production in 2027, continuing development of future chip generations.

Covered by 4 sources

More on this story

The full stack behind abundant intelligence
16d· 2 sources

#ai-hardware #ai-inference-chips #asic #broadcom #gb200-superchip #jalapeno #nvidia #openai

More in Chips & Compute

Chips & Compute

DOJ Probes Nvidia’s Tie-Up With Groq on Antitrust Concerns

Covered by 2 sources12h ago

Chips & Compute5 min read

D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion

Covered by 2 sources2h ago

Chips & Compute5 min read

Celero raises $275m to bring coherent optics inside AI data centres

The Next Web2h ago