AI · Official
OpenAI Explains Why It Built the Responses API for Developers
OpenAI Developer changelog (mirror) ·
At a glance
OpenAI has explained the reasoning behind the Responses API, a new interface for use with GPT-5. It points out the limits of the existing approach and says the API is designed for reasoning models and AI that completes multiple steps on its own.
Key points
- Responses works differently from one-message-at-a-time chat. It repeats a cycle of thinking and using tools.
- It carries the reasoning process (the thinking steps the AI goes through before producing an answer) into the next step, which OpenAI says makes it more efficient.
- It also returns records of tool use and intermediate steps, which OpenAI says helps with debugging and review.
Why it matters
As AI increasingly works through multiple steps, the basic connection method developers use is changing, which makes this important.
Original source
Why we built the Responses API
OpenAI Developer changelog (mirror) · Sep 22, 09:00 KST
Read on OpenAI Developer changelog (mirror) ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to OpenAI Developer changelog (mirror).
More from this field
- OpenAI Opens ChatGPT Space to Plus Users for Pages, Slides, and Team Sharing
OpenAI opened ChatGPT Space to Plus users on the 20th, local time. Space works as a new home for pages, slides, images, files, and uploads. Users can write pages with ChatGPT, add interactive charts, turn ideas into slides, and invite others to edit together.
AI 매터스 · Nov 21, 11:26 KST - Anthropic Researcher Claims Claude Helped Prove Riemann Hypothesis, Experts Await Review
Wes Roth covers a claim by Anthropic researcher Levent Alpöge that he proved the Riemann Hypothesis with help from the AI model Claude. He looks at the huge Lean formal proof, reactions from mathematicians and AI safety researchers, and what this could mean for AI and math.
Wes Roth · Nov 21, 11:24 KST - AI Claims Proof of 167-Year-Old Riemann Hypothesis With Anthropic's Claude
An Anthropic researcher, Levent Alpöge, says he and Claude found a proof of the Riemann Hypothesis, a famous 167-year-old math problem. He released a version written in Lean, a language that checks math proofs by computer, and also claims to have solved a broader generalized version. Experts called it a potentially historic moment but said the proof still needs careful checking.
매일경제 · Nov 21, 11:21 KST