OpenClaws or OpenClaus?

OpenClaw is the Santa Claus of children everywhere. Why, if I am to believe the stories I hear, it is delivering most of what Musk is promising to deliver with an Optimus future!

Here’s what I see happening:

For a year or two now, this whole “agentic AI” thing has been promising that you’ll have at your disposal your own “Chief of Staff”. Such phrases are used by LLMs as part of some sort of fixed point argot feedback with their human users. You’ll see phrases like “lean into” etc. making their way into the human shibboleths to signal to each other that they’re “in the know” about all this AI stuff. There is now emerging a class of people who are spending huge amounts of money per month on subscriptions to the more advanced LLM versions. Combine these two and you have the Smart Set.

Meanwhile, back here on the farm, those of us without access to Codex et al, make do with our puny little non-agentic coding assistants and whatever passes for our multi-decades of experience that might provide something that actually solves the problem of helping individuals deal with their day to day lives in a world where they’re being forced into gig economic status.

For example, as part of my attempt to get a leg up on this, while I’m waiting for GPT5.2 to get through answering a query for code modification (GitHub - jabowery/vibemod: Coding assistant can't produce correctly formed patches to your Python? Use this.) I’ve looked into Upwork as a place where I can bring in enough money to at least increase the number of queries to Claude for basic programming tasks – at which it is pretty good if you can get the spec right.

Although I was aware of this before, it is obvious that Upwork needs some Work. Specifically it needs to put the individual “seller” in a better position to negotiate.

The Chinese markets used to have this tradition (of which I learned from my SO who was stations with her ex-husband in Taiwan while he was doing U2 Mao-flyovers):

Buyer and Seller each write down their bid and ask and then if the bid is higher than the ask, they split the difference and move on to the next transaction with others.

Generalizing this to system that optimizes a marketplace based on my experience with BTC arbitrage, algorithmic trading, business planning, political economy based on rNPV liquidation value property money, etc etc, I came up with something that I could conceivably implement as I wait for GPT5.2 for up to a half-hour to answer a query for small program mods – or wait for DAYS while Claude (whatever – eg 4.6) stops blocking me from using its superior ability to write code to spec.

Let me give you an idea of what OpenClaus can NOT do as “Chief of Staff”:

Keep track of all the constraints on what resources you have and their scheduling in anything remotely resembling a PERT/GANTT calendar, and maintain a big board prioritized by what you personally value given that “in the long run we’re all dead”.

The last one – about “dead” – is particularly relevant as my brother has just retired from being an ER physician and has complained about being stressed out because he can’t keep track of all the little projects that he’s been putting off all his career. That’s what motivated me to start thinking about this as a use of my time while I’m waiting for these increasingly expensive “grad students” to work on my primary objective:

But for some strange reason, “Hume’s Guillotine” isn’t among the shibboleths like “lean into” and “Chief of Staff” with which you can identify members of The Smart Set.

3 Likes

rNPV is Importance
-∂rNPV/∂t is Urgency


Of course this is just one of the dimensions I’ve reduced in the aforementioned “market” where you might need not just to triage but also arbitrage based on the make-buy tradeoff in delegation to unbound agents’ resources. Contractually bound agents’s resources are presumably dispatchable. And both kinds of resources carry the attendant risk adjustment based on their performance history (ie: credit rating whether internally audited or externally provided) – risk that goes into the ‘r’ of the rNPV.

2 Likes

Well hush my mouth! I DO have access to Codex with my basic subscription to GPT but I ended up getting stung financially by it when it was first coming out. The version I tried was one with incremental charges that accumulate the more the agent(s) go round and round palavering – not the flat rate per month one. I honestly don’t recall how I ended up in that situation but my impression was that I couldn’t get the flat rate GPT to provide Codex.

In any event, I’m using it now and it’s better than Claude.

PS: It’s good to see Musk facing a tiny bit of reality here but he’s already falling so far behind I’m not sure he’ll be able to catch up. Grok is really bad and I don’t think it is because xAI hired the wrong people. It wasn’t even that Musk hired the wrong guys to do the hiring per se. The latter is because the same parasites that tell him not to think about abolishing the 16th Amendment in favor of a net asset tax on liquidation are the ones doing the actual hiring of the people who do the hiring.

Musk’s brain parasites are deeply embedded. I suspect the degree of introspection that will be required to dig them out may take with them a substantial portion of Musk’s brain.