Hey! I resemble that comment :-P (I still tend to use apt-get out of habit...)

No, I read it. Machine needs handholding because it makes spagheti code.

This can be easily automated away!

He didn't say they weren't ? He said youtube keeps recommending 'cringe' shorts no-one wants to see. I can sympathize with him - I have the youtube recommends the same 4 videos over and over again in multiple categories issue, and the 'lots of shorts I don't care about issue'. Though, shorts at least get refreshed/rotated more often then the stupid suggestions.

>> but is it a question whose answer matters?

I think it does? "scummy person loses job, finds another way to cash in" almost seems to becoming a trope? I think it raises questions about what is left _out_ of the book, not just what's in it - are the issues raised the worst/most important, or just the ones that will sell the most books? Did we really need someone to 'tell us' meta/social media can be evil?

There are reasons that (some) criminals are not allowed to profit from books/movies about their crimes.

Anyway, that's just my general feelings about this sort book - I've never heard of the book or the author. And I honestly have no interest in reading it. Based on what I'm reading here - that would basically be rewarding/enriching one of the 'bad actors' ?

you can write automated MCP tools that run within claude code, and could theoretically generate as high a load as any other automated/3rd party agent. You can also do loops that burn tokens incredibly fast. This is allowed with no caveats (I use MCP's basically to test what I'd like to try with the API...) So this explanation just seems a lil hollow.

When you can’t enforce everything at once, you go where the most acute problems are. I imagine when your MCP avenue of abuse catches on—like this other category of harnesses did—to such a scale as to become a problem impacting us folk trying to go about our business… when that’s where the problems shift, I imagine (and hope) Anthropic will crack down on that vector too. To keep the service usable for us ordinary meatbags.

I’m glad they give us the leeway to experiment, and I’m also glad they weed the garden from time to time. To switch metaphors, I’m deeply frustrated when my very modest, commuter-grade use gets run off the figurative highway by figurative hot-rodders. It’s been extra-529y this week, and it’s about time they reined it in a little.

You’re always welcome to pay-as-you-go for as many tokens as you’d like to burn on their infrastructure… or to compute against any of the wide array of ever-improving open models on commodity compute providers…

>>when your MCP avenue of abuse catches on

Thats an interesting way of phrasing it - so is there a way to use the quota that's not 'abuse'? MCP/claude code seems to be want they want you to use it - are loops or ralph abuse as well ?

I take your point, the way I used “abuse” there probably carries more charge than I’d meant it to. It’s a totally valid way to use the technology, it’s “abusive” only of the subscription program. And I agree: Anthropic clearly want people to industrialize and automate usage. But that’s not what the subscription product is for. Use all the loops you want, burn all the tokens you want—just pay what they cost.

> is there a way to use the quota that's not 'abuse'?

I think my answer is “no.” In that I’ve never thought of the limits as “quotas,” and I don’t think I’ve heard Anthropic speak of them that way. Quotas are to be used up, while limits are to signal that what you’re doing is outside the envelope of acceptable use. Quotas are to be met, limits are to be avoided.

I interpret the intention of the subscription, like a membership at a makerspace, to be to allow novices to experiment with stuff, to take on personal-scale projects, to allow them to learn without having to understand the tool’s economics upfront. To play without fear of expensive mistakes.

And, like the makerspace, it can only offer generous limits to the extent that most of us rarely bump up against them. If you’re doing production runs in the makerspace, you’re crowding out the other members, and something’s gotta give.

To the extent that we do bump against the limits during “ordinary” use—and we do with Claude Code, especially those of us around here—it’s really frustrating. The limits need to rise in order for it to remain attractive to casual users like me, the economics still need to add up for the subscription program as a whole, and part of that is separating out what patterns of use belong under a different regime.

If these harnesses or OpenClaws or whatever stop making sense as soon as they have to pay their actual costs, then that’s a pretty good sign they’re abusing the spirit of the subscription.

But Anthropic seem more than happy to service those uses via the API or metered usage, and even to sweeten the deal with more reliable access and bulk discounts. I certainly wouldn’t characterize the same automated usage as “abuse” via that channel.

>>I take your point, the way I used “abuse” there probably carries more charge than I’d meant it to.

Fair enough.

>> But that’s not what the subscription product is for.

This was the point I was trying to make - I pay for XX tokens/usage. But somehow using them all is 'taking advantage' ?

BTW - I'm actually not complaining about the limits - I probably only use half my tokens on average week. I'm just annoyed at having to jump thru hoops if I want to try something 'API' oriented. For me, AI is still the new shiny - I try all different sorts of things learning/playing. There was an article posted today about writing agent harnesses. That could be interesting - maybe I want to try my hand at it. But then I've got to mess around/pay extra to _try_ something I that my subscription already easily covers.

[added:] >>to take on personal-scale projects, to allow them to learn without having to understand the tool’s economics upfront. To play without fear of expensive mistakes.

This is exactly what I'm trying to do - however, as soon as you want to try anything 'API' oriented, the 'fear of expensive mistakes' comes right back.

It's not difficult at all to burn through your weekly limit just writing code.

Yes, but very few people are actually doing that compared to OpenClaw. If everyone else was doing that, they'd be cracking down on it too.

While you can write an automated tool to consume all their tokens, I strongly suspect most users, like myself, are not doing that. So even if Anthropic loses money on a power user, they profit overall and keep public sentiment high by not alienating users with restrictions. It's an optimization problem of making a profit off the average used while staying low enough to attract customers, even if that means some users cost more than they pay.

More users spinning up OpenClaw means that balance starts to shift towards more users maxing their tokens, thus the average increases, so I think their explanation makes sense still.

>>So even if Anthropic loses money on a power user, they profit overall and keep public sentiment high by not alienating users with restrictions

So they profit overall if I use all my tokens either way? Again, I understand usage limits - I just don't understand why some usage is 'good' and some 'bad' if I'm using the same either way.

>>More users spinning up OpenClaw

I'm pretty sure that's a small percentage of overall users, and probably skewed towards the very people that would be recommending/implementing you model for work/businesses. Seems like that would be the group you are encouraging/cultivating ?

Anthropic is much more concerned about what people are ACTUALLY doing than what they could, in theory, be doing.

My company has several MCPs that our very token intensive, but it seems that with Claude Code, usage is throttled even before hitting limits. I don't have any proof, but often when using intensive MCPs, Claude Code will just stall for 10+ minutes.

I wonder if anyone else has experienced this?

This is what I've been wondering about for a while now. I have the 20x plan as well, which I thought would allow me to try some API coding - but you get zero API usage.

As you said, I would imagine where the token usage comes from is irrelevant - you are generating the same load whether you do it from claude code or some other agent. So it seems like the rules are more to do with encouraging claude code usage, rather then claude model usage.

Claude code is still getting used by these agents. They banned the mimicry awhile ago and said claude -p was fine.

OpenClaw just happens to also get telemetry, of probably higher value, out of the same tokens. It also happens to be owned by their competitor.

edit: I'm wrong OpenClaw surprisingly doesn't collect telemetry. Good for them.

IIRC the Stratus/Model 88 was Moto 68K chips, not x86? I worked on them for years on wall st. - really nice machines! :-D

The ones I encountered (and I never worked on them directly) were tandem-x86 systems and ran windows.

According to Wikipedia they launched in 2002, so I guess they were quite new when I saw them in 03.

"we" paid ISP's ... which in turn, paid for infrastructure. Some of "we" pay cable providers for internet service, which in turn paid for (in my case) fiber-to-the-curb. Advertising basically supported social media, search engines, etc.

An article about old school bbs'ing and no-one mentioned 'door games' ?? Tradewars 4 evah !!

Heh - QWK was such a god send for those of us paying long distance charges to access boards. I think I used 'Bluemail' ? 'Bluereader' ? and really liked it.