Both are just Codexes running in a permanently rolling session in dedicated UNIX user accounts. They're wired up to Maildir so receiving a mail activates Codex and makes it read the new message, there are autonomy wakeup timers, they have accounts in my bug tracker and CI systems. They're currently useful for:

• Triaging and working on customer support tickets. Sometimes I wake up and the fix/response for a ticket filed by a customer is already there waiting for my approval. Recently I started letting them directly interact with customers in specific scenarios.

• Triaging the bug backlog. One of them decided to spend its "free time" finding old bugs that were fixed without being properly closed, or are dupes, so it's cleaning up detritus in the tracker.

• They obviously do all the coding and debugging by just assigning tickets.

• They keep an eye on a "pet" server the company has, and have proven able to fix it in the past when it ran out of disk space.

• They handle non-business projects I have for them.

• They help out with the release processes.

The dedicated home dir is very useful and they use it all the time as part of coding and investigating tricky issues.

My setup relies heavily on email, as everything bottoms out in email anyway. Watching them mail each other out of the blue to coordinate stuff is pretty cool.

The catch with offerings like Grok Bot and Dots is that it is a slippery slope towards letting the labs keep the agent's learning and SOPs. That is where we should draw the line. Agentic coordination _has_ to be built with open protocols and OSS implementations, we as users need to push for the intelligence to be a commodity, and most importantly we need to make sure that we own the agentic team's learnings.

So why don't I just have Claude write notes and summaries on specific things, and then it will always have a knowledge base? Am I missing something? I mean, if Dots and Grok Bot are not an extra charge / extra compute, then I guess that's fine, but in Claude Code you can make a AGENTS.md or CLAUDE.md file, and if you put it into any directory, Claude will read it when accessing that specific directory, so if its in your root where you launch Claude, your new Claude instance will read it and have all that in a dedicated smaller context window. But as it edits code, it can read the smaller ones too.

IMO best to keep work and personal data segmented on the hardware level. It's better for opsec in every single way and helps if you were ever to be subpoena'd or raided, your work laptop would be the only in-scope device for search/seizure.

Take off your "engineering" hat and put on your "normie" hat...

OpenAI's Dots, Meta's Muse, xAI's Grok Bot, etc are trying to target non-technical people and give them "24/7 AI personal assistants". Apple is also pursuing this angle by adding more features to the new Siri (partnership with Google-Gemini).

Perspective of product and market : we need our AI to be more deeply intertwined with customers lives instead of just being on-demand chatbot Q&A sessions. The "sticky" product to create this customer relationship is "AI personal assistants". Instead of just providing "answers" (chatbots) -- provide "completed tasks" (AI assistant).

Perspective of technical predecessors and concepts overlap : OpenClaw and Hermes self-hosted software on Mac minis and Linux boxes as "personal assistants" is geared for techies instead of normies. Instead, repackage those types of tools for normal people in cloud VMs to be hosts for "long-lived agents". Zero install required.

Probably this.

> I guess the intent was to pull together the Codex, claw and ChatGPT Work paradigms and simplify them?

Probably this in part, too. They're trying to figure out how to decouple agent lifetime from conversation lifetime, without accidentally making it too useful for end users.

I noticed in the past that tooling - both for AI and in general - tends to miss the features that would make it most useful. Like, look how long did it take for the AI vendors to supported "scheduled runs", and they're still offering only toy-level configuration for that[0]. Wonder how many years it'll take to allow users to configure external triggers, and whether it'll be sooner than forced re-authentication will become frequent enough to make the feature useless in the first place.

--

[0] - I understand they don't want users to run this too often, or to accidentally end up spawning a job every 10 minutes - but with limits on frequency in place, there is otherwise no good reason for this to be a limited dropdown, instead of the "repeats every" configuration that every calendar app and phone app already uses.

That's how I understand it.

Cloud compute means its work VM is isolated from your devices, so it can't destroy your local data as easily (unless it has access to your devices) and it's on 24/7. A big negative is that you are giving access to even more of your services and data to a third party and the lock-in into a walled garden happens once you start depending on it.

So everyone is trying to give the aunts, cousins, neighbor's dads some of the agent capabilities that developers have been closer to.

That said, there's the other 10% here that is not necessarily new capability unlocks vs codex, but general product experience that can have some benefit to people already used to what the latest models can do

This is exactly where I'm at with AI. (Mostly via Claude Code, but I'm not sure the harness, or my workflow in particular, is the important part.)

I am increasingly wondering though, is there really a valid reason to keep blocking on my approval? Most of the time, I wind up saying yes anyway, because the model has a valid, efficient solution.

What if it's faster at this point to just fix the mistakes?

Scary thought, but it seems like we're close, or already there.

In the morning I come and look at the work and decide what to do next. It's great in that sense.

But not great for peace of mind. Because now there's always something to be done overnight...

Same thing in the development world. I need to do something when version x of some thing gets released. If I can instruct a bot to do it and it's safe enough (e.g. read only), then why not.

Are you sure? Based on their marketing video, usually you just have to tell it to swap one of the later slides or photos to put it first. :)

Oh, also you have to tell it those times you want to prioritize your children on your calendar.

Maybe people are ok with that, but I feel like it would be nicer to just sell a cheap SBC like a raspberry pi that you can plug in (and unplug!) and just pay for the tokens used instead of having your data stored offsite and paying cloud prices.

However, it is the case that other industries like 3d graphics and so forth have experienced a frontier shift so perhaps there’s still some advancement