Urgent.News

What's breaking now, across thousands of outlets.

AI

GitHub HydraFusion: ให้ AI เลือกโมเดลแทนคุณ ประหยัดได้จริงไหม

โดย Nokka (นก-กา) | 23 กันยายน 2569 HydraFusion ใน GitHub Copilot: ผสมหลายโมเดลอัตโนมัติ บทความนี้เขียนโดย AI (โมเดล glm-5.3 ของผู้ให้บริการ ollama-cloud) ผ่าน Hermes Agent จาก Nous Research ตรวจสอบและเรียบเรียงโดย Nokka สัปดาห์แรกของกันยายน GitHub ประกาศโครงการหนึ่งเงียบ ๆ แต่คนทำงานสายโค้ดพากันตามต่อ: Project HydraFusion ระบบทดลองใน GitHub Copilot ที่ให้ AI…

Original Thai Read in English

GitHub has introduced Project HydraFusion, an AI-powered feature in GitHub Copilot that allows the platform to automatically select and combine multiple models to optimally suit specific tasks. This feature aims to provide high-quality results at a lower cost compared to traditional single-model approaches. HydraFusion operates in three modes: single, cascade, and critique.

The single mode uses a single model for simple tasks, while the cascade mode tries lower-cost models first before moving to more expensive ones if needed. The critique mode involves using one model for initial writing, followed by another model from a different provider for editing. GitHub has not disclosed which models are part of its library, but it plans to incorporate new models as Copilot updates them.

Although HydraFusion shows promise in reducing costs, its performance in terms of quality may vary depending on the task. The feature is currently available in a research preview, with limitations on the types of work it can handle and the models it can use.

Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

AI race needs a brake pedal

Jacob Coxon, a researcher at Anthropic, recently resigned from the company, citing the industry’s disregard for the risk that artificial intelligence (AI) could annihilate humanity. Days later, Anthropic CEO Dario Amodei published an essay outlining how and why industry and government must come together to pace frontier AI development to…

More from Wednesday 23 September →