Tech

OpenAI’s Dots boundary problem rate doubled in longer tests

The New Stack By Amanda Caswell Sep 30, 2026 · 10:26 AM 5 min read 4 views 0 comments

OpenAI’s new Dots are built to keep working after you step away. Launched at DevDay on Tuesday, the always-on agents

The post OpenAI’s Dots boundary problem rate doubled in longer tests appeared first on The New Stack.

The New Stack Original story · thenewstack.io

Read the full story

How does this story make you feel?

👍 ❤️ 💡 😮 😂 😢 😠

Discussion (0)

No comments yet. Start the conversation!

The New Stack + Follow

Section: Tech + Follow

Up next from The New Stack

Your AI agent aced the demo. Your data may still derail it.

Ahhh, demo AI agents. Don’t you just love them? Cute and cuddly, solving all your company’s problems without complaints, missteps, The post Your AI agent aced the demo…

The New Stack Sep 30, 2026

OpenAI Launches dots: Always-On GPT-6 Astra Agents That Work From Their Own Cloud Computers

MarkTechPost Sep 29, 2026

Tech

OpenAI’s Dots are always-on AI agents for work

PCWorld Sep 29, 2026

Tech

OpenAI just launched Dots. Here’s why they matter for developers.

The New Stack Sep 29, 2026

Discussion (0)

More to read

OpenAI Dots Run Read-Only Research When Nobody Is Asking via @sejournal, @MattGSouthern

Introducing dots

OpenAI’s Dot agent is enterprise software that can also order your dinner