So if I understand this it is an OpenClaw type system but based on the Claude Code Agent SDK? And they suggest installing it on a VM? Or is there more to it?
OpenClaw runs on your machine or an ephemeral sandbox. Each session starts fresh. Phantom gets its own dedicated VM that persists. The ClickHouse instance it built three weeks ago is still running and queryable.
OpenClaw spends a lot of tokens on screen understanding and vision loops. About 60% of its skills are basic macOS-level computer use (clicking, typing, reading the screen). Phantom skips that entirely and uses the Claude Agent SDK directly, so it gets full shell, file system, git, web search, and MCP tools natively without the token overhead of parsing screenshots.
The biggest difference is probably dynamic MCP. Phantom registers its own MCP tools at runtime, and they persist across restarts. It built a ClickHouse REST API, registered it as a tool, and now any Claude Code session or other agent that connects to it can query that data. It builds its own capabilities and exposes them as an API.
It also has persistent vector memory across sessions (Qdrant, local), a self-evolution engine where a different model validates every config change, and we built a companion tool called Specter (https://github.com/ghostwright/specter) that provisions VMs with DNS, TLS, and systemd in under 90 seconds, so deploying a new Phantom is genuinely three commands.
Both are good projects, different approaches. OpenClaw does computer use well. Phantom is a persistent co-worker that lives on its own machine and compounds over time.
> OpenClaw runs on your machine or an ephemeral sandbox. Each session starts fresh. Phantom gets its own dedicated VM that persists
Yeah like any claw type system will be if you install it on a VM. I think the self-tooling thing is interesting but you'll gain by emphasizing that over the VM thing - at least with a technical audience.
I'm fascinated to know the kind of work that allows you to intelligently allocate so much resources. I use Claude extensively and feel that I great value out of it but I reach a limit in terms of what I can do that makes sense relatively quickly it seems.
I haven't tried any of these products, but I do have a senior dog with very severe separation anxiety. She barks and destroys stuff the minute I step out the door until the minute I come back. I could keep her from destroying stuff with a crate, but the neighbors would still throw a fit about the barking.
Effectively, this means that I have to hire a dog sitter every time I leave the house without her, just like an infant. If dog tv could fix this problem for me it would create an enormous amount of economic value.
On the contrary, this gives me hope it's possible to create value for people even when you compete with hundreds of free Youtube playlists. This is good!
You see, in any sane world the input box that can answer almost any question in the world should be more profitable than Netflix-for-dogs. But I bet it's not.
Often these "spam" reports by end users are just accidental clicks as well. Many of the abuse reports we get are like an email from someone's Mum and visibly legitimate. At other times there are users who use the Report Spam function as a kind of inbox management tool - a way of moving mail away so they don't have to see it because Trash or Delete or whatever is just further away from their pointer.
I tell my friends and family to never click unsubscribe links, unless they had proactively subscribed. Buying something from a company that requires an email does not count. unsolicited marketing emails are spam and should be treated as such. Double so if that company sends marketing emails disguised behind support@company.com.
No, sending marketing from support emails is almost certainly trying to game spam filters. Marketing@company.com would work for the allow replies purpose.
"Report spam" is quicker and easier than "unsubscribe".
Gmail added a popup asking the user if they want to unsubscribe when flagging a newsletter with the appropriate unsubscribe headers, so it must be common enough to warrant Gmail developer attention.
Thing is, unsubscribe links are often an "inform spammers that this mail address is in use" link. Even the ones Gmail offers up.
If I didn't click their button to subscribe, I'm not clicking their button to unsubscribe. Who's to say they won't just "sign me up" again after a while? In fact I know several large US corporations which routinely sign you up for notifications again after a few months.
If you didn't click the button, then of course, you don't send the unsubscribe message.
If you did subscribe to a newsletter and no longer want to receive it (which is the majority of these cases), then the unsubscribe action is the logical thing to do.
> If you did subscribe to a newsletter and no longer want to receive it (which is the majority of these cases), then the unsubscribe action is the logical thing to do.
Doesn't sound exceptional to me. Most of the authors I have some personal knowledge of manage through exactly that: spouses, grants, book sales, residencies and teaching creative writing.
Compared to the postal workers, accountants and insurance agents named in this article they can count as exceptions too, save for the creative writing teachers.
I think Don DeLillo quit his job before his first book and never looked back.
Surely only economists get excited by the revelation that consumers have to have money to buy things. I'd say domestic service is going to make a comeback. I do think I'd make an excellent man servant. Eke out my later years being ever so slightly superior to my employer without ever being openly insolent. Hang on...
If this scenario comes to pass, then the class war in labor markets will have been won by capital. That would spell the end of the promise of non-violent resistance. What other leverage would ordinary people have if their labor is worthless?
Blue collar work is somewhat insulated so long as humans are cheaper and less fickle than robots.
We have seen in Gaza and to native americans what capital/power does to populations deemed surplus. It's not pretty. of course, that kind of violence happens once their land is desired, before that they are simply repressed.
I think if the superintelligence hypothesis really does happen, we will need to have a rapid accommodation for the bulk of the population or things will get quite out of control.
I was at a restaurant last night with a group, and it was the first time I heard people actively organizing on how to block new data centers in the area. It felt like being in a scene in a sci-fi movie.
I do think if these feedback loops happen too quickly of white collar displacement, there might be some real violence against data centers.
That seems possible, but if people are severely displaced for a significant duration, damage to property is going to seem quaint if there is no New Deal.
Better at reading yes but not necessarily better at comprehension which is what I believe people are getting at in these discussions. I read and listen. Initially my comprehension and memory while listening was inferior, but you can learn the skill of deep concentration on audio (or some may have it natively).
reply