throwpoaster

I recommend running this by legal if you are funded, however, I am not a lawyer.

> The transition Apple and Tim Cook announced today is entirely different. No one’s hand was forced. There is nothing unpleasant.

Tim Cook is a master of supply chain logistics and was the perfect choice to scale Apple into global production.

As global supply chains collapse; as Apple fights for fab space with Nvidia, and loses; and as Apple releases products like the five-core Neo, which can monetize a stock of six-core phone chips with single-core faults, and they're still stocking out; transitioning to a CEO with a hardware background will enable a different set of strategic choices.

Mr. Cook is jumping before Apple is pushed, but that's not the same thing as a move being unforced.

We’re looking at you, Vancouver.

No, if you ran Openclaw using Anthropic API as a provider, or had it use the ‘claude -p’ cli interface, you got an email from Anthropic threatening a ban unless you upgraded billing.

This was widely reported, and happened to me. You probably can’t reproduce it or see it in docs because they seem to have changed the policy.

> CAN rail to port to transPac/Asia is cheaper than rail/truck to US post tariff (most commodities now). Also it's ~75% of CAN exports goes to US, and it was only structurally cheaper under pre-Trump trade arrangements, now it's structurally more expensive.

The Port of Vancouver’s sulphur export capacity is prebooked for several years. Even with the sulphur boom caused by the Hormuz blockage we are unable to ship it out, but we can rail it out (sorta — cars are booked up too). Many such cases.

Shipping logistics are cheaper _when they work_, and we just went through a shipping demand destruction cycle in 2020 _and_ shipping insurance rates are going up because of naval conflict.

> half commodities half goods

Strong agree. We need secondary processing. The decades-long Liberal push for a postindustrial economy has completely failed.

1) The argument in the article is that he will join the fight against AI when he wins the fight against LLCs.

2) You start an LLC and use it to build and sell a product customers want. Then you, your family, and your community, can economically untether from, for example, bosses who don’t care you’re autistic and need you to smile in meetings.

I’ll join Doctorow’s fight against LLCs when I understand how to create economic freedom for my family and community without them.

My standard question about Swiss engineering, “how many jewels?”, is failing me.

Yeah, we only recently began honouring our agreements[0], and even then we did it my recategorizing non-military spending as military[1].

[0]: https://nationalpost.com/news/canada/history-canada-nato-mil...

[1]: "That five per cent figure is somewhat deceptive, since just 3.5 per cent of that will go to core defence needs, while 1.5 per cent is to cover spending loosely related to national security — such as funding for maritime ports, airports and other infrastructure." - https://www.ctvnews.ca/politics/article/pm-carney-declares-u...

Canada and America are neighbours. It is far cheaper for Canada to ship things south into a giant market than to ship east and west into our own, smaller markets. Trading with anyone else in the world entails much larger shipping expenses. This is structural, and applies to something exceeding 90% of our trade.

Carney is wrong, but he's not a fool. I read this as high-level virtue signalling to two audiences: Canadian left-patriots, who love to hate America while (unknowingly) free-riding on the benefits of the relationship. He has a vulnerable majority and is smart enough to plan ahead for the next election. Over half of Boomers support the Liberals, so he is playing to their emotions. He doesn't need to play to their pocket books, because they're mostly as rich as they're going to get, so he can trade economics for votes.

Second: he's signalling to China, and other international trade partners, that we are open for business. Carney has been struggling with pro-China (former) members of his caucus also being pro-slave-labour[0]. This is a message that, as he indicated in his Davos speech[1], he is willing to be flexible on Human Rights if the price is right.

America hasn't changed. When Trump is gone the American export market will remain.

Carney is wrong, but he's not a fool. He's amoral.

[0]: https://www.youtube.com/watch?v=LFHgR4vAurg

[1]: https://www.weforum.org/stories/2026/01/davos-2026-special-a...

Gumption and a firm handshake!

Regarding the recent thread[0] on writing a python interpreter in python, this is Ken Thompson’s famous paper on writing a C compiler in the C, and the class of exploits thus enabled.

[0]: https://news.ycombinator.com/item?id=47755261

How does it define ‘\n’? ;)

cf: https://www.cs.cmu.edu/~rdriley/487/papers/Thompson_1984_Ref...

"Agentic Coding/Terminal/Search/Analysis/Etc"...

False: Anthropic products cannot be used with agents.

Anthropic gonna acquire Cloudflare for stock. Solves their infrastructure problems in one shot.

The noise we make is hurting _us_. Decibel levels in cities are unconscionable.

We have more than enough calories globally, although Africa has more starvation now than it did a decade ago.

What we need is nutrient density. 0% of those feed calories have, eg, creatine. 100% of the beef calories do.

Generally, across AI providers, I have come to interpret sudden degradation in existing capabilities as a signal that a new, more expensive, product tier is about to launch.

Have you tried asking Mythos for a fix?

Wait what? If I get told to come back in three hours because I'm using the product too much, I get penalized when I resume?

What's the right way to work on a huge project then? I've just been saying "Please continue" -- that pops the quota?

If you struggle with procrastination please get assessed for ADHD.

A positive diagnosis is life changing.

Shuttle was awesome and the people who love to hate it can personally fight me.

How long have you had an agent performing the same task, or trying to improve performance towards the same outcome?

I’m not really talking about coding. I’m talking about autonomy.

A comment that takes a second to realize it’s a troll.

Repeatability (see my response to op).

Skills and MCP are useful for when you need to repeat specific processes, perpetually. Without them the task description and reasoning falls out of the context window, or is compressed, and the process fails.

An agent will eventually forget, or hallucinate, guardrails and requirements. Yes to AGENTS.md, but when you're actively managing the whole context window in a long-running task you don't want to just keep jamming stuff in there and hope for the best. Skills help budget tokens and stabilize around specific outcomes.

If your use case is not agentic, as you build a skill corpus you can begin having the model reason at higher and higher levels about the outcomes you're aiming at.

Eg: I'm super lazy now and ask Claude to launch the project instead of just running the command myself. This is probably best done as a skill.

They’re different things. You can have skills using MCP.

“A sculptor drove a truck to fund his art.”

"Why does the country with the fifth highest GDP per capita have better infrastructure than the country with the ninth highest?"

Yes.

All new technology has issues. Figure it out.

Especially if you're spending $3k per month on inference, have the model fix the agent.

I suppose the idea is to wait for someone else to productize it.

Lazy.