I am on the Claude Max 20x plan, and this still happens when using Fable 5/Opus 5. I would run out of weekly quota in 2 days, whereas Opus 4.8 would last the entire week, and sit at about 80-90% at the end.
Same here. Over the last two weeks I switched back to Opus 4.8 and turns out that still seems to last the week like it used to. These new models must be eating tokens.
Using ASD-STE100 is in my system prompt, not just CLAUDE.md which basically never gets followed.
I actually converted it from the PDF into an explicit skill with the word list inline as well as the main rules.
Works a little bit, but give it a bit of context and the model’s training takes over and it starts talking like a dictionary-huffing crack addict again.
It’s a model problem and no amount of harness hacking seems to fix it.
I put it in a hook, and Claude basically re-evaluates every changed comment that it makes against a prompt in the hook. This burns tokens, but my company pays for it, so I don't care.
I mean I do the same at work where we currently use Anthropic, but we are also on a token optimisation drive so it’s getting hard to justify spending even more tokens cleaning up after Anthropic’s garbage by paying Anthropic more.
We have started having users use GPT 5.6 Sol to compare quality and effficiency over Opus. Fable not happening at work because of the data sharing clauses and the completely nuts pricing.
How long will the petrodollar remain a thing with the current diversification of energy sources proceeding apace internationally?
Listening to Americans talk about energy and vehicles feels like going back in time, they’re stuck in the past and things that worked then and the world is rapidly routing around them. Quite sad to see.
The petrodollar thing always seemed overhyped by people who don't understand economics that well. It was just a term for the dollars received by oil producing countries like Saudi Arabia.
People used dollars rather than yen or pounds because it the US was the largest and a rather free and stable economy. That still mostly applies.
The argument in the linked article:
>Since the 1970s, global oil transactions have been priced and conducted almost exclusively in U.S. dollars. That arrangement has given America an unparalleled advantage, effectively creating an economic blackmail chip.
I think is bunk. A country pricing in Euros would make no difference apart from traders needing to check the dollar euro rate.
> A country pricing in Euros would make no difference apart from traders needing to check the dollar euro rate.
You can't clear nation-scale oil purchases by looking at the exchange rate, which is predicated on there being sufficient liquidity at that price for the transaction you're looking to make.
The petrodollar is both a demand and supply solution, and you're looking at this in micro rather than international macro terms.
The demand explanation is simplest -- the largest producers of a limited-source, universally-required commodity demand that purchases be made in US dollars.
As a result, all countries need access to dollars in order to make those purchases at scale.
Enter the supply side, where dollars both aren't and kinda-are physical. They aren't, in that international transactions are obviously executed with digital balances. They are, in that arbitrary countries can't just "create" dollars as needed: they must get those dollars from someone who has them.
Ultimately... the US Federal Reserve, who is empowered to create new dollars.
Putting all of this together, you have an aggregate demand for dollars of {US federal budget, similar to other countries' monetary demand} plus {international float for transacting dollar-denominated commodities}.
It's that second piece that people are really referring to when they say things like 'the petrodollar allows the US to run deficits that would negatively impact other countries' currencies'.
Because as Doctor Strangelove quipped, it is not only necessary but essential for this system's smooth functioning that the US produces large enough numbers of excess dollars to meet international demand.
The fly in the ointment, so to speak, has been the 00s+, initially War on Terror, now War on Et Al., US weaponization of the dollar against countries doing things it doesn't like.
Hence Russia/China's dream of breaking the petrodollar.
One piece of evidence - around 2020 the US went from being an oil importer to an oil exporter and people hardly noticed.
I also think if Saudi asked to be paid in Euros rather than USD it wouldn't make much difference. People just change currencies into what they need. They are just tokens to facilitate the trade of goods and services like oil for Ferraris in Euro or oil for Boeings in USD. The forex markets are huge.
Ironically, the US being an oil import / exporter is the least important country to this system, given it's the only one able to arbitrarily inflate the US dollar supply.
The forex vs oil scale is valid point, and it'd be curious to compare it across the decades.
Per some preliminary numbers, Brenton Woods being abandoned in 1971 led to market forex volume substantially growing every year.
Oil:forex looks like ~1:150 in 1980, scaling to 1:500 in 2010.
So indeed an increasingly smaller portion of the forex pie.
Abit glib to call it hyped when the US has started multiple wars to protect the petrodollar.
Trying to do business any other way puts targets on whole countries, much less the speaker and their family. Many attempts were made in the middle east and Africa to make that change, and those people and governments were wiped out.
While the argument can be made for it's economic effect and power today vs 20 years ago, I don't think it was overhyped then.
I'm a Brit and we've done business other ways for centuries without issues. At least not issues due to using pounds rather than dollars. Who got wiped out?
I’m a heavy LLM user but if someone gives me an AI-voice argument and presents it as their own, I reflexively dismiss everything they say going forward.
Funny, I'm the same. And if find Sol way more pleasant to work with, not to mention way faster. And Sol's compacting is superior, I haven't yet run into it forgetting something crucial from the pre-compact conversation, meanwhile Fable does that notoriously.
When they eventually make Fable available to cheapest plan, I'll downgrade. It's worth keeping for reviewing the code and the UI tasks, but nothing else.
reply