At least theoretically, the bill would work on a “wallet” system, where you fill up your account with $X every month, and then you’re charged per use. That keeps there from being a huge bill, worst case you’re just on hold until the next fill up.
I’m not familiar with the Claude Code subscription, but with Codex I’m able to use millions of tokens per day on the $200/mo plan. My rough estimate was that if I were API billing, it would cost about $50/day, or $1200/mo. So either the API has a 6x profit margin on inference, the subscription is a loss leader, or they just rely on most people not to go anywhere near the usage caps.
The bundle only works if it’s +EV for them. A lot of analyses (though not all - it’s complicated) say that the $200/mo bundle (and certainly the $20/mo bundle) costs more than that for most users, and the bundle is currently a loss leader. If so, then eventually prices will need to go up, and API per usage pricing will seem much more attractive.
Dhaka muslin most famously isn't producible today due to a lack of knowledge. More broadly a lot of weaving techniques have been lost since they don’t make sense to do with machinery.
I don’t disagree that there are a lot of gains, including on net, just that it hasn’t been a pareto improvement with no losses at all.
Cloth absolutely has gotten worse over the last two hundred years since industrialization. It's also orders of magnitude cheaper, making it worth it, and certainly new types of cloth are available that weren't before, but we're not better off in every possible way.
It would be impressive in the sense of "Can I ask AI to make me money, and it does so autonomously?", since that's just a free source of money (until other people do it better than you and with more capital). But looking at everything here, I'm dubious that the AI will be able to do that. Farming isn't that high of a margin business, and it's adding a lot of inefficiency and other issues (small acreage, unbelievably low amounts budgeted for labor and machinery, dubious plan for "IoT Sensor Kit", no budget for seeds, etc.).
Ironically, Ghibli's adaptation of A Wizard of Earthsea (written by Le Guin, an American author) flopped in part because Miyazaki made it much more about heroes versus villains than the original story.
A related issue is “vote for my preferred candidate, or I’ll abuse you” as a way for husbands to control wives. That’s especially relevant when one party is favored by a majority of men while the other party is favored by a majority of women.
Sure - the problem is that the almond farmers are being incentivized to grow almonds by giving them a significantly below market cost. If the the costs reflected reality, almonds wouldn’t be profitable.
Just looking at my own usage at work, we’re spending around $50/day on OpenAI API credits (with Codex). With Claude Code I get higher usage limits for $200/month, or around $8/day. Probably the equivalent from OpenAI is around $100/day of API credits.
Maybe OpenAI has a 12x markup on API credits, or Anthropic is much better at running inference, but my best guess is that Anthropic is selling at a large loss.
My 32 GB MacBook Pro sits at about 50%, even after months of being powered on, unless I'm running programs that use a lot of memory. That's at least what Activity Monitor reports, perhaps Activity Monitor reports it in a different way.
Because Claude Code is not a profitable business, it's a loss leader to get you to use the rest of their token inference business. If you were to pay for Claude Code by using the normal API, it would be at least 5x the cost, if not more.
> Developers want to use these 3p client and pay you 200 a month, why are you pissing us off
Presumably because it costs them more than $200 per month to sell you it. It's a loss leader to get you into their ecosystem. If you won't use their ecosystem, they'd rather you just go over to OpenAI.
Presumably Claude Code is a loss leader to try to lock you into their ecosystem or at least get you to exclusive associate “AI” with “Claude”. So if it’s not achieving those goals, they’d prefer if you use OpenAI instead.
I’m not convinced that that’s an accurate view of Wikidata. Wikidata is a basically disconnected project. There is some connection, but it’s really very minimal and only for a small subset of Wikipedia articles. Wikipedia is 99% just text articles, not data combined together.
Frankly, I think the reason people haven’t built apps on top of Wikidata is that the data there isn’t very useful.
I say this not to diss Wikimedia, as the Wikipedia project itself is great and an amazing tool and resource. But Wikidata is simply not there.
I have a friend who has someone who has repeatedly threatened to assault her, and her primary protection is keeping her address hidden from him. Should she never be allowed to own a house at risk of being assaulted?
Look at the data - it had already been on the downslide for years before LLMs became a meaningful alternative. AI was the killing blow, but there was undoubtedly other factors.
It’s essentially a federal law - if a state wants to get full federal funding for highways, they have to have a law restricting alcohol purchase and public consumption to 21+. It’s from the National Minimum Drinking Age Act of 1984.
The journey it makes is 90 minutes and it can charge for that journey in 8 minutes. Offloading and onloading the thousands of passengers (and 220 cars!) takes much longer than the 8 minutes for the battery to charge.