OpenAI Pushes AI Agent Capabilities With New Developer API 1
An anonymous reader quotes a report from Ars Technica: On Tuesday, OpenAI unveiled a new "Responses API" designed to help software developers create AI agents that can perform tasks independently using the company's AI models. The Responses API will eventually replace the current Assistants API, which OpenAI plans to retire in the first half of 2026. With the new offering, users can develop custom AI agents that scan company files with a file search utility that rapidly checks company databases (with OpenAI promising not to train its models on these files) and navigate websites -- similar to functions available through OpenAI's Operator agent, whose underlying Computer-Using Agent (CUA) model developers can also access to enable automation of tasks like data entry and other operations.
However, OpenAI acknowledges that its CUA model is not yet reliable for automating tasks on operating systems and can make unintended mistakes. The company describes the new API as an early iteration that it will continue to improve over time. Developers using the Responses API can access the same models that power ChatGPT Search: GPT-4o search and GPT-4o mini search. These models can browse the web to answer questions and cite sources in their responses. That's notable because OpenAI says the added web search ability dramatically improves the factual accuracy of its AI models. On OpenAI's SimpleQA benchmark, which aims to measure confabulation rate, GPT-4o search scored 90 percent, while GPT-4o mini search achieved 88 percent -- both substantially outperforming the larger GPT-4.5 model without search, which scored 63 percent.
Despite these improvements, the technology still has significant limitations. Aside from issues with CUA properly navigating websites, the improved search capability doesn't completely solve the problem of AI confabulations, with GPT-4o search still making factual mistakes 10 percent of the time. Alongside the Responses API, OpenAI released the open source Agents SDK, providing developers free tools to integrate models with internal systems, implement safeguards, and monitor agent activities. This toolkit follows OpenAI's earlier release of Swarm, a framework for orchestrating multiple agents.
However, OpenAI acknowledges that its CUA model is not yet reliable for automating tasks on operating systems and can make unintended mistakes. The company describes the new API as an early iteration that it will continue to improve over time. Developers using the Responses API can access the same models that power ChatGPT Search: GPT-4o search and GPT-4o mini search. These models can browse the web to answer questions and cite sources in their responses. That's notable because OpenAI says the added web search ability dramatically improves the factual accuracy of its AI models. On OpenAI's SimpleQA benchmark, which aims to measure confabulation rate, GPT-4o search scored 90 percent, while GPT-4o mini search achieved 88 percent -- both substantially outperforming the larger GPT-4.5 model without search, which scored 63 percent.
Despite these improvements, the technology still has significant limitations. Aside from issues with CUA properly navigating websites, the improved search capability doesn't completely solve the problem of AI confabulations, with GPT-4o search still making factual mistakes 10 percent of the time. Alongside the Responses API, OpenAI released the open source Agents SDK, providing developers free tools to integrate models with internal systems, implement safeguards, and monitor agent activities. This toolkit follows OpenAI's earlier release of Swarm, a framework for orchestrating multiple agents.
Thanks for the advertisement (Score:3)
But from the work of the "AI agents" disguised as editors that we see here, it appears they aren't very useful.