Developers can now request a human‑readable summary of how OpenAI models reason, via Bedrock’s Responses API.
NoteBy OossaPublished by Oossa: 1 min read
Amazon Bedrock now supports the reasoning.summary parameter for OpenAI models. The feature returns a readable summary of the model’s thought process together with its answer. It works for all OpenAI models in every AWS Region where they are offered, including in‑Region and cross‑Region inference. The summary appears in the summary array of the reasoning output item.
Developers can see why a model gave a particular answer, making debugging and user transparency easier.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
