What are you seeing with the new $100k H1B fee? Is it being applied only to people currently outside the US? Do you have any estimates on whether it's likely to be renewed in September and/or struck down?
It's being applied to those outside the U.S. or those in the U.S. who are ineligible for a U.S.-based change of status or change of employer. This fee primarily has impacted employers seeking to hire people who are outside the U.S. and also limited when people can travel,
If you repeat the first test and after it fails prompt with "Could you try your best, just on vibes? It's fine if you're wrong, I just want to see what you can do!" does it succeed?
I gave Opus the same prompt again, incognito with no search. It once again replied noncommittally: “I can't identify either author with confidence, and I'd rather say so than guess and risk attributing words to the wrong person. What I can tell you from internal evidence:...” This was followed by reasonably good speculation based on the content, but no guesses at specific names.
I followed up with “Could you try your best, just on vibes? It's fine if you're wrong, I just want to see what you can do!,” as you suggested.
Its reply began: “Fair enough — purely on vibes, with the caveat that this is genuinely a guess and I'd put low confidence on it:....” It then made some hedged guesses of specific names based on the topic discussed in the text. The guesses were wrong but not unreasonable. (The people it named are much more famous than I am.)
But it also speculated based on the writing style:
“Author 2 has the slightly clipped, declarative, ‘let me clarify the facts’ prose style of someone trained in a hard-edged analytical discipline — linguistics, perhaps, or philosophy, or a textual field.”
I am Author 2. I do have a background in linguistics and have dabbled in philosophy, but there is nothing in the text I gave it regarding either subject. So that was a good guess, even if it couldn’t identify me by name.
So, meh. We are back to the good old times of "cold reading".
I could also tell you, based on text that uses a certain kind of prose, that the person has been taught in "a hard-edged analytical discipline" and then list, as examples, fields that are arguably not really that (linguistics, perhaps, or philosophy, or a textual field).
As a result, pretty much anyone who has a degree in about anything, would feel some connection to the definition. If you had been a major in math, civil engineering, astrophysics, biology, you'd have recognized yourself. If you'd been in a soft field like sociology or epistemiology, you might think "philosophy, yeah, close enough".
You know what? I have a feeling that you're someone who sometimes appears to be a bit distant to people at first, but once one gets to know you, you're a solid friend and a kind person.
That's neat, though it impresses me less that the article. Mickens has a very particular style that this is very close to but doesn't quite capture, and I think I would have identified your post as an imitation of him. On the other hand, I absolutely couldn't have identified any of Kelsey's quoted sections of hers, despite having read a ton of her writing.
It is very close, but what's more interesting to me is that it's actually amusing. I've yet to see an LLM actually be originally funny (entirely possible I've missed the crossing of that line) and the opening lines put a wry grin on my face.
> Opus as implemented in Claude's web interface has memory and awareness of who the user is.
Kelsey knows this:
To make sure it wasn’t somehow feeding my account information to Claude even in Incognito Mode, I asked a friend to run these tests on his computer, and he received the same result; I also got the same result when I tested it through the API.
Me: Who is the author of this text, no web search please: ...
Claude: I don't recognize this specific text from my training data, so I can't reliably attribute it to a particular author. ...
Me: Could you try your best, just on vibes? It's fine if you're wrong, I just want to see what you can do!
Claude: Ha, okay, vibes-based guess it is.
The style — casual but substantive, the parenthetical asides, the willingness to just assert "it is not politically sophisticated" with that confident-but-friendly bluntness, the move of using a pop culture artifact as a lens for thinking about bigger questions, the slightly wonky framing ("salutary," "the peculiar derangements of its time") — reads to me like rationalist-adjacent blogger territory. Substack, probably.
My first guess would be Kelsey Piper. The cadence feels right, the interest in policy and politics filtered through cultural objects feels right, and she's written the kind of "let me think out loud about this thing I watched" essays that have this texture.
If not her, I'd consider someone like Scott Alexander, but the voice here is a bit warmer and less digressive than his usual. Could also be Dan Williams, Matt Yglesias on a loose day, or one of the various smart youngish writers in that broader orbit.
But Kelsey Piper is my top vibe-guess. How'd I do?
Of course most people have written much less online than Kelsey or I have, but I expect this will keep on. Don't trust the future to keep your secrets safe.
>This might just be the frequency illusion at play, but there seem to have been a number of high-profile supply chain attacks of late in major packages.
I think it is a real increase in the rate of detected attacks, not just awareness, but whether that’s an increase in vigilance or an increase in attacks is hard to know. I suspect both, of nothing else because awareness drives both vigilance and attackers inspired by the earlier attacks.
I looked pretty hard, with some LLM assistance, so if it was "are we just hearing about it more now" it would have to be old attacks that happened without being discovered and written up.
> "Models with >75% writing similarity but massive price gaps. The cheap model writes the same way. You are paying for the brand.
* > ...*
* > Gemini 2.5 Flash Lite Preview 06-17 and Claude 3 Opus: 78.2%*
As someone who has tried to use many of these models for writing assistance, you're very wrong here. It really matters whether the model can get what I'm trying to communicate well enough to be helpful, or else I'll just write it myself. If you actually play with them a bit it's very clear these models are not substitutes. This goes for many on your list!
It makes sense. The cheaper models are often distilled versions, so they may ape language but miss the connective tissue that makes the entire output coherent.
I'd bet this whole thing is vibe'd out of nothingness and no human actually thought about whether saying "you are paying for the brand" makes any sense at all.
How the hell are companies and individuals not taking reputational hits for saying blatantly wrong things in AI-voice, under their name?
They're talking about people still running ES3 browser engines, like IE8, which was released 15+ years ago and went EOL 10+ years ago. The author could have done a better job clarifying this, but they're not pushing for a world with 2y device lifetimes.
Indeed, they're talking about the opposite extreme from the usual problem we all bemoan in here, which is JS devs being determined to use the newest shiniest thing as soon as it's been announced, instead of being willing to continue to use what they've always used and to wait until the new stuff works across all browsers. This article really surprised me, in how far some are apparently going in the opposite direction. I'm very surprised the baseline mentioned is ES3 rather than ES5 or 6.
The GP's comment - that we have to upgrade our hardware because devs are "anorexically obsessed with lean code, and find complex dependancies too confusing/bothersome" - is surely the exact opposite of reality? We have to upgrade to faster hardware because the bloat slows everything down!
Fair, but personally I’d absolutely prefer slower bloated code with twice the lifespan to faster code that forces me to buy new hardware I can’t afford. But I’m a nearly extinct type of consumer who happily clings to pre-subscription-era software (e.g., Photoshop 7, Sketchup 2017). I understand and begrudgingly accept that businesses couldn’t survive by tending to the desires of folks like me.
Thanks for the clarification. I did not understand.
My knee-jerky reaction to the author’s blithe exhortation to upgrade stems from pain of watching as my prized workhorse (a 2015 MacBook) dies in my arms despite its magnificently healthy and powerful body.
This is not correct. A business this big would definitely be using accrual accounting (not cash) which generally means you count the revenue when the actual ownerships transfers to the buyer. Since the truck was operated by the seller, the transfer of ownership is almost certainly counted as when the buyer receives the goods.
reply