for the last few months i have been working on long running persistent agents. i believe this is the next paradigm shifting product after chatgpt and codex. there are a number of challenges, and i'm currently writing a longer post with some learnings & thoughts on why i believe the next big unlock is solving theory of mind loose thoughts: - the next paradigm-shifting product after chatgpt and codex is the persistent personal/work agent - the blocker to making such agents is that our models can't "read the room" - reading the room sounds soft but it's deep theory of mind - reading the room is the difference between talking to a bot and talking to an embodied identity you can trust to accomplish tasks and communicate with your colleagues - reading the room an understanding of who "your person" is, their desires and motivations, and who your audience is - concretely, it's tracking what i know vs what my user knows vs what the room knows. information asymmetry as a first-class skill - part of this is understanding compartmentalization. enterprises call this tenting and workspace isolation. "if my user is part of this tent, don't divulge information in a broad channel that's not also tented" - if i give a friend my home address, i trust them not to announce it in a room of a thousand people. I do not yet trust a model to exercise that same discretion. - harnesses like openclaw keep trying to solve this at the application layer with permissions, workspace isolation, context injection, and increasingly elaborate agent harnesses. necessary for now, but this likely futile as the final answer. discretion has to live in the model - side effect: this is also part of why model writing reads as slop. good writing is meeting your audience where they are. same missing skill tldr: persistent agents live or die on reading the room, and theory of mind may be one of the last major gaps before agi

A billion users can now create and publish websites from their phones with ChatGPT Work. But most people don’t really grasp the full extent of the capabilities here. From your phone, you also have access to: - Cloud computer (15 GB RAM) - Persistent workspace & files - Terminal and code execution - Remote browser - Connected plugins (Slack, Gmail, GitHub, etc.) - All your personal finances, transactions, bank statements - Scheduled tasks - Git clone & PR creation - Build & deploy websites - Create docs, sheets, and slides - Inbox/calendar summarization - Website monitoring & alerts All at your fingertips, using a simple chat interface, no laptop required. All you have to do is switch to the Work tab on your ChatGPT app.

Absolutely beautiful rant about AI in Linux Kernel from Linus yesterday: I realize that some people really dislike AI, but this is an area where I'm willing to absolutely put my foot down as the top-level maintainer. Linux is not one of those anti-AI projects, and if somebody has issues with that, they can do the open-source thing and fork it. Or just walk away. AI is a tool, just like other tools we use. And it's clearly a useful one. It may not have been that "clearly" even just a year ago, but it's no longer in question today. There are other questions around AI (like what the economy of it will actually look like in the end), but "is it useful" is no longer one of those questions. Anybody who doubts that clearly hasn't actually used it. Yes, it can also be a somewhat painful tool, both for maintainer workloads and just from a "it keeps finding embarrassing bugs" standpoint. But the solution is not to put your head in the sand and sing "La La La, I can't hear you" at the top of your voice like some people seem to do. The solution is to make sure those LLM tools _help_ maintainers instead of just causing them pain. There's no question on that side. We're not forcing anybody to use it, but I will very loudly ignore people who try to argue against other people from using it. And no, AI isn't perfect. But Christ, anybody who points to the problems at AI had better be looking in the mirror and pointing at themselves at the same time. Because it's not like natural intelligence is always all that great either. The kernel project has been and will continue to be about the technology. Sure, the social angle of working on open source is important and often a very motivating part of the project, but in the end that's a side benefit, not the _point_ of the project. This is *NOT* some kind of "social warrior" project, never has been, and never will be. In the kernel community we do open source because it results in better technology, not because of religious reasons. And so we make decisions primarily based on technical merit. Not fear of new tools. Linus

Your ChatGPT subscription now powers an OpenClaw agent that genuinely feels magical to talk to. Previous OpenClaw releases had OpenAI models running, but they never quite let the models reach their full potential. That changes today. Personality is now deliberate, tool calls land exactly where they should, and your agent actually follows through on what it says it will do. OpenClaw is now running on top of the Codex harness by default. In handing the inner loop to OpenAI's native Codex harness, we eliminated the conflicting instructions and duplicate tools that used to make the model hesitate. What we stripped out under the hood: - Duplicate tools (no more guessing between Codex native vs OpenClaw versions) - Conflicting instructions (no more NO_REPLY vs message tool ambiguity) - Leaked context (heartbeat logic only appears on actual heartbeat turns) Less context bloat. More room for the agent to think. And here's what we inherited for free, thanks to the Codex App Server: - Searchable dynamic tools. Roughly 5,500 fewer upfront tokens per turn, which means faster and cheaper. - Auto-Review mode using the built-in Codex guardian. - OpenAI's native plugins (Calendar, Email, Drive) running in the same thread. For you, the result is a personal agent that actually feels personal. It picks up where you left off across any channel, handles things before they hit your radar, and only breaks your flow when it has something genuinely worth showing you. For developers, the result is stability. Because the inner loop runs on OpenAI’s native Codex harness, every upstream improvement lands in your agent automatically. To get started, paste this in terminal: > openclaw onboard That is the whole setup.