Chokepoint risk does more than spike the spot price for a season. It re-prices geography permanently: it redirects the next decade of pipeline and terminal investment and hands a windfall to whoever sits on the alternative route.
But the problem is these agents are just naturally pretty sloppy and they're naturally pretty spiky in their capability profiles. And so you wouldn't necessarily even if you noticed a weird error that it made, you wouldn't necessarily jump to the conclusion that it was like because of some sort of malign crazy conspiracy.
The cabin is a classic literary setting. It's the getaway spot where characters can flee to escape their troubles or journey to in order to find new ones.
Yeah, I mean I feel like uh the models have been getting a lot better at sort of agent-based longer running coding tasks and it seems pretty clear that they are now actually pretty capable and depending on exactly your definition of of junior engineer it seems pretty spot-on I would say.
But if we fast forward half a century, this is the 787, their latest airliner, which by the way was launched more than 20 years ago. You can't spot the difference. It doesn't fly any faster. It doesn't make the world any more accessible.
What stands out about Hsieh's version is that her roots occupy such a unique spot in history: her grandparents were Chinese born in Indonesia, which means they got caught between the rock of the Cultural Revolution and the hard place of anti-communist backlash.
then the quantity of everything that's not a ballerina, say, goes to infinity, but our the marginal utility in that stuff goes to zero faster than the quantity is rising.
when I think about why it might be good to have a lot of wealth in the future as a good classical utilitarian, to me, the value is or at least one way you could have a kind of almost unsatiating uh utility function in in having wealth in the future is to create new happy beings, right? They just add to the total welfare of the world.
13 years ago, at the Wired 2013 event in London, I was asked when robotaxis would arrive there and as a joke, gave an answer of June 22, 2026 that turned out to be impossibly spot on.
exceptions are an inherently poor way of handling errors because they make it easier to write bugs which won't be immediately obvious on casual code inspection
You can give it a Bash tool so it can ripgrep its way through the codebase. You can give it some queryable codebase index, an LSP server, a vector database. In the end it doesn't matter much. The bigger the codebase, the lower the recall. Low recall means that your agent will, in fact, not find all the code it needs to do a good job.
Immediately cease trying to perform meaningful work via a chatbot (e.g. ChatGPT, Gemini on the web, etc.). Chatbots have real value and are a daily part of my AI workflow, but their utility in coding is highly limited because you're mostly hoping they come up with the right results based on their prior training, and correcting them involves a human (you) to tell them they're wrong repeatedly.
If I was put on the spot to name the greatest movie of the 21st century, I would probably say Michael Hanneke's Amour, an achingly moving, relentlessly unpleasant portrait of an elderly couple sinking into illness and senescence, forced into making the grimmest decisions possible.
The reason I think MCP may be a one-year wonder is the stratospheric growth of coding agents. It appears that the best possible tool for any situation is Bash—if your agent can run arbitrary shell commands, it can do anything that can be done by typing commands into a terminal.
While there is some utility value in DeFi, it basically lets users transform custodial risk into technical risk (e.g. bridge protocol hacks), which is not a free lunch.
This is the best screenshot utility for Macs. You’d think how much can there be in a screenshot utility, and CleanShot X will still color you surprised.
I think people think evolution is, like, perfecting things in some way. And they're not. They're bodge jobs, you know? That's why we have a blind spot in our eye, but things like squid don't.
shame has been sharpened into a tool for cultural coercion and compliance. That what people have figured out is that shame is a is a soft spot on almost everybody. And if you press that spot, people will shrink. They will run away. It is particularly used against women, but it is used against large numbers of people to cause them to not take an action.
Yet lime is a huge blind spot for economic historians, despite it increasing the productivity of what was still by far the largest portion of the economy: agriculture.
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com.
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.