Anthropic adopts OpenAI's markdown instructions spec
The move ends a compatibility headache for developers who had to maintain separate prompt formats across the two major AI vendors.
Anthropic has decided to support OpenAI's markdown instructions specification, according to The Register. The spec standardises how model instructions are formatted, and Anthropic's adoption means developers can now use the same markdown-based prompts across both major AI platforms without rewriting them.
The Register reports that developers had been dealing with a compatibility headache, maintaining separate instruction formats for Anthropic and OpenAI models. The news was greeted with relief, as it removes a significant source of friction in multi-vendor AI development workflows.
This is a single-source report, so there is no independent confirmation or contrasting view to weigh. The Register's account frames the decision as a pragmatic response to developer pressure rather than a strategic partnership announcement.
More in Compute & Hardware
Accelerated Server Sales Show Accelerating Growth
A report from The Next Platform finds that sales of accelerated servers are growing at an increasing pace.
FCT Unveils Flex Circuit Leak Sensor for AI and HPC Liquid Cooling
Flexible Circuit Technologies has developed a custom leak-detection flex assembly aimed at protecting AI and high-performance computing systems from coolant failures.
Hardware Trojan Detection: Stable Patterns Found in Gate-Level Netlists
A new study from UW-Madison and Marist shows that RTL Trojans leave stable structural and signal-flow traces that can be localized at the gate level.
DKRZ Joins EU Project for AI Climate Models on HPC
Germany's climate computing centre is part of a new four-year Horizon Europe effort to make AI-based climate models usable on European supercomputing and AI infrastructure.