Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding13m ago AI agents are flooding public services with new requests20m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit54m ago 10 of the scariest AI villains in movie history55m ago Maven Robotics wants to steal your robot deployment deal56m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford59m 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 Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports1h ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion2h ago Andrew Tulloch, Poster Child for Out-of-Control AI Spending, Reportedly Quits Meta2h ago Mother Horrified When Meta’s AI Scours Instagram and Facebook for Invasive Information About Her Young Daughters2h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises2h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google2h ago

Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding13m ago AI agents are flooding public services with new requests20m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit54m ago 10 of the scariest AI villains in movie history55m ago Maven Robotics wants to steal your robot deployment deal56m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford59m 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 Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports1h ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion2h ago Andrew Tulloch, Poster Child for Out-of-Control AI Spending, Reportedly Quits Meta2h ago Mother Horrified When Meta’s AI Scours Instagram and Facebook for Invasive Information About Her Young Daughters2h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises2h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google2h ago

Dev Machine Learning5 min reading time

Keenable AI Open-Sources NEEDLE: A Live Search Benchmark That Rebuilds Its Query Set Every Hour

MarkTechPostPublished 10 days ago

Keenable AI has open-sourced NEEDLE, a live benchmark for web search APIs that regenerates query sets hourly or daily from fresh public data sources. It evaluates 15 search APIs across multiple domains using a pooled oracle to assess retrieval performance.

#evaluation-frameworks #information-retrieval #keenable-ai #needle #search-benchmarking

More in Dev

Dev6 min read

How Credit Genie keeps codebase docs fresh with OpenWiki

LangChain2h ago

Dev19 min read

Article: When Spec-Driven Development Pays Off

InfoQ (AI, ML & Data)6h ago

Dev19 min read

Deploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM

AWS Blog17h ago