Nemesis
3.2K posts
Over the last two weeks, Codex got a lot closer to a general work agent
It can now use more of your computer, inspect what it builds, create richer artifacts, and keep longer-running work moving
English
Workspace agents are surprisingly powerful. Powered by Codex under the hood, the same implementation we have open-sourced here: github.com/openai/codex
OpenAI@OpenAI
Introducing workspace agents in ChatGPT—shared agents that can handle complex tasks and long-running workflows across tools and teams.
English
These are cool! I think most companies will want to use them.
OpenAI@OpenAI
Introducing workspace agents in ChatGPT—shared agents that can handle complex tasks and long-running workflows across tools and teams.
English
We are releasing a *research preview* of Chronicle in Codex. It allows codex to build up memories based on your day to day work on your computer and then refer to these memories to be a lot more helpful.
Available for PRO subscriptions and on Mac to start. This is early and consumes quite a bit of tokens, but it has changed how I and many folks at OpenAI use Codex.
OpenAI Developers@OpenAIDevs
Last week, we released a preview of memories in Codex. Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context. Now, Codex can help with what you’ve been working on without you restating context.
English
Now available in research preview on Pro and Max on macOS.
Enable it with /mcp. Docs: code.claude.com/docs/en/comput…
English
Your work tools in Claude are now available on mobile.
Explore Figma designs, create Canva slides, check Amplitude dashboards, all from your phone.
Give it a try: claude.com/download
English
@AnthropicAI @AnthropicAI @claudeai Max user here. This started today. My normal usage pattern didn't change, but the meter shows a full week's quota drained in a single day. If this is expected, please clarify the change. If not, please investigate urgently.
English
New on the Engineering Blog: How we designed Claude Code auto mode.
Many Claude Code users let Claude work without permission prompts. Auto mode is a safer middle ground: we built and tested classifiers that make approval decisions instead.
Read more: anthropic.com/engineering/cl…
English
@AnthropicAI We need an urgent response. I'm on Max, my usage pattern did not suddenly change, yet your meter shows a full week's quota drained in a single day. This looks like broken accounting or an undisclosed limit change. Please address this urgently.
English
First Codex, now Gemini today - nearly a week’s wait. But I’m confused, since I actually have an Ultra plan. It could be a coincidence, but I’ve also hit a limit on AI Studio at the same time.
The labs have dramatically cut back, though. I was getting a LOT more messages from each of them before this week. Reality check.
English
@noahzweben Please fix dispatch it wad not working from two days and now it consumed max user weekly limit in few hours
Its frustrating
English
Dispatch can now start coding tasks with specific models. Tell it to use a specific model in natural language.
We want to keep making Dispatch the most useful place to delegate Cowork and Code tasks.
How can we make Dispatch better for coding use-case?
English
@AnthropicAI If anyone else on Max is seeing this, please reply with what plan you're on and roughly when it started. Trying to figure out whether this is isolated or broader.
English
@AnthropicAI I'm a Max user and Claude's usage limits don't seem right. I've never hit my limit before, but now it says I used a full week's limit in a single day. What changed? Can someone look into this?
English
@AnthropicAI For context: my normal usage pattern hasn't changed much, which is why this sudden weekly-limit exhaustion looks unusual. Is this a bug, a policy change, or a counting issue?
English
@AnthropicAI I'm on Claude Max and the usage meter appears wrong. I normally never hit limits, but today it says I used a full week's quota in one day. If this is expected, can Anthropic clarify what changed?
English
@AnthropicAI @DarioAmodei Also tagging you here — I'm a Max user and Claude's usage limits don't seem right. I've never hit my limit before, but now it says I used a full week's limit in a single day. Can someone please check this?
English
@AnthropicAI @claudeai Also tagging you here — I'm a Max user and Claude's usage limits don't seem right. I've never hit my limit before, but now it says I used a full week's limit in a single day. Can someone check?
English
@AnthropicAI Multi-agent is impressive! Speaking of agents - Cowork dispatch agent is broken. Messages from phone show as read but Claude never responds or acts. 2 days, Max plan, latest version. This needs fixing urgently.
English
New on the Anthropic Engineering Blog:
How we use a multi-agent harness to push Claude further in frontend design and long-running autonomous software engineering.
Read more: anthropic.com/engineering/ha…
English