JioHotstar Benchmarks Six Code Retrieval Approaches for AI Coding Agents

JioHotstar evaluated six code retrieval approaches for AI coding agents using SWE, CodeScale Bench, and an internal question-answering harness, finding structural search performed well on concrete tasks.

Read the full story at InfoQ AI/ML ↗

Timeline · 1 report

2026-11-11 14:28 · InfoQ AI/ML
JioHotstar Benchmarks Knowledge Bases for AI Coding Agents

More stories

Google DeepMind launches Gemini Robotics 2.5 after Apollo 2 humanoids hit 96% in Mercedes-Benz test — Google DeepMind Blog
Anthropic IPO said to be multiple times oversubscribed as it targets $1.4 trillion valuation — CNBC Technology
Nvidia board probes CEO Jensen Huang over alleged affair with suspected Chinese spy — CSET Georgetown
Nvidia spy scandal exposes Singapore networks channeling AI chips to China — New York Times AI
OpenAI's quarterly revenue rises 50% to $10 billion, but operating losses widen — The Information AI
Claude Code permissions file exposes thousands of API keys and secrets, researchers find — VentureBeat AI
OpenAI launches Businesses in ChatGPT beta with verified profiles and Business Agents — OpenAI News
CoreWeave beats Q3 revenue estimates, rules out new unsecured debt through 2027 — The Globe and Mail

Get the daily brief of stories like this at 6:30 every morning →