Product news and engineering notes from the team building endue.
Three days after launch, a second look at Gemini 4 Argon from an operator's seat. Where it leads and trails by type of work, what a task really costs, what a 1M-token output and a guardrail-free tier mean for how you run agents, and what you can prepare before the API opens.
A tour of the endue console, from the home board to approval cards, the Studio canvas and Spaces. Why the interface of an agent product is a control surface, how many minutes a fixed layout saves, and how often other AI apps rearranged their screens over the last four months, with dates.
Google's first Gemini 4 model leads 12 of the 18 benchmarks it published, writes up to 1M tokens per response and starts at $2/$10 per million tokens. Only vetted cyber defenders can use it today. Here are the key numbers, what independent testers measured and where people are skeptical.
Google's first Gemini 4 model leads 12 of the 18 benchmarks in its own table, and the public leaderboards mostly agree. This post goes through who ran which test, how many tokens Argon spends per task, what a 1M-token response costs, and why only cyber defenders can use it today.
Three days after launch, a systems view of Dots. It covers the cloud computer each one runs on, how a goal turns into actions, the checks that sit in between, what OpenAI's own tests say about where it slips, what changed since DevDay, and what you would need to build the same thing yourself.
An engineer's look at ChatGPT Space three days after launch. How spaces, pages and files fit together, how access is inherited, what each person's agent can see, what the Compliance API exports, and what is still missing, from export to version history.
Artificial Analysis puts GPT-6.1 Sol one point below GPT-6 Astra at under a quarter of Astra's cost per task, and at about a tenth of Claude Sonnet 5.5's despite the same list price. Early user tests, live OpenRouter data, switching gotchas and the safety numbers.
OpenAI launched Dots a day after holding back GPT-6.1 Astra and apologizing to Australia. What its own safety numbers and privacy FAQ say, how the first day went (stalled demos, a five-hour outage), and a checklist built from OpenAI's help articles.
After DevDay, users divided OpenAI's new Pro multiples by price and watched Ultrafast empty a weekly limit in under 30 minutes. We checked the math against OpenAI's docs and collected OpenAI's follow-up comments and a guide to picking a plan.
OpenAI's DevDay announcements from September 29, sorted into five groups. From Dots, the always-on agents, to GPT-6.1 Sol, ChatGPT Space, Codex and the new plans, see what shipped, who gets it and when.
Dots, OpenAI's headline DevDay launch, are agents with their own cloud computer that stay on in ChatGPT, Slack and Teams and keep working between conversations. What they can do, who gets them, and how permissions and approvals work.
OpenAI launched GPT-6.1 Sol at DevDay. It costs the same as GPT-6 Sol and scores close to GPT-6 Astra on coding, computer use and document work. What changed, what Ultrafast adds, and which model to use when.