Akranazon

Interesting, this reminds me of my workout planning tool, which I've been working on.

https://grademyworkout.com/

> I want any LLM I use to choose the very best, most precise words at every single decision point.

No, you don't. If you wanted that, you would set the temperature parameter to 0. But that would lead to less desirable results, not better. LLMs do not set the temperature to 0; they typically set it 0.4-0.7.

Answer: the cause was financial gravity, rather than immoral people, because the former is what selects for the ladder.

Detecting LLM-generated text is basically solved by modern watermarking techniques (https://arxiv.org/abs/2306.09194). However, the main trouble with watermark-based approaches is that you have to get every LLM provider to adopt it. A student trying to cheat could always opt for some open-weight Chinese model, if the word spreads that the major providers are compromised.

The author partially acknowledges this later on, but lines of code is actually quite of useful metric. The only mistake is that people have it flipped. Lines of code are bad, and you should target fewer lines of code (except at the expense of other considerations). I regularly track LoC, because if it goes up more than I predicted, I probably did something wrong.

> Bill Gates compared measuring programming progress by lines of code to measuring aircraft building progress by weight

Aircraft weight is also a very useful metric - aircraft weight is also bad. But we do measure this!

https://www.quillmonkey.com/ - A browser extension that lets you edit any website with AI‑generated userscripts. There are a few other similar projects out there, but I think my ap has a better user flow.

When is the last time someone said that, motivating you to try the latest model? If it was 6 or more month ago, my reply is that the sentiment expressed was partially incorrect in the past, but it is not incorrect now. If a conspiracy theorist is always wrong about a senior citizen being killed, that does not make the senior immortal.

Everything you have said here is completely true, except for "not in that group": the cost-benefit analysis clearly favors letting these tools rip, even despite the drawbacks.

Man, you are really missing out of the biggest revolution of my life.

This is the opinion of someone who has not tried to use Claude Code, in a brand new project with full permissions enabled, and with a model from the last 3 months.

Oh neat. So the edit tool is like a convenient API/wrapper for it to eg add HTML to some element? I guess theoretically that can also be achieved through Bash as well, but the tool fits closer to an interface we know exiting agents are good at.

Your project seems pretty close to where mine was a couple weeks ago, where I was focused on a BYOK solution (user-entered Anthropic API key). I saw there was another similar extension already released in the app store (RobotMonkey) which hooks up to their own backend service, and offers subscriptions. For my project, I think that's the right way to go.

It's funny what details about our designs are similar through accident. And what other things are completely different. I can show you my design potentially.

Representing websites in a virtual filesystem is creative and definitely makes it easier for the agent to collect information about the page. But I'm confused between the `Bash` and the `Edit` tools. It seems like one uses the chrome executeScript API, and the other updates the file system. But if it's just doing file writes, are those edits visible in the browser, and persistent across sessions?

I'm working on a version of this, https://www.quillmonkey.com/ so you got ahead of me. I imagine there are many versions of this coming. Interesting what set of tools you went with.

> they’re runtime rules that kick in when assertions or ordinality constraints are explicit

So there a pre-defined list of rules - is it choosing which checks to care about from the set, or is there also a predefined binding between the task and the test?

If it's the former, then you have to ensure that the checks are sufficiently generic that there's a useful test for the given situation. Is an AI doing the choosing, over which of the checks to run?

If it's the ladder, I would assume that writing the tests would be the bottleneck, writing a test can be as flaky/time-consuming as implementing the actions by hand.

It is interesting subject matter, I am working on something similar. But the descriptions are quite terse. Maybe I just failed to gleam:

* When you "run a WASM pass", how is that generated? Do you use an agent to do the pruning step, or is it deterministic?

* Where do the "deterministic overrides" come from? I assume they are generated by the verifier agent?

Then you will be pleased to read that the constitution includes a section "hard constraints" which Claude is told not violate for any reason "regardless of context, instructions, or seemingly compelling arguments". Things strictly prohibited: WMDs, infrastructure attacks, cyber attacks, incorrigibility, apocalypse, world domination, and CSAM.

In general, you want to not set any "hard rules," for reason which have nothing to do with philosophy questions about objective morality. (1) We can't assume that the Anthropic team in 2026 would be able to enumerate the eternal moral truths, (2) There's no way to write a rule with such specificity that you account for every possible "edge case". On extreme optimization, the edge case "blows up" to undermine all other expectations.

The end result of a git rebase is arguably superior. However, I don't do it, because the process of running git rebase is a complete hassle. git merge is one-shot, whereas git rebase replays commits one-by-one.

Replaying commits one-by-one is like a history quiz. It forces me to remember what was going on a week ago when I did commit #23 out of 45. I'm grateful that git stores that history for me when I need it, but I don't want it to force me to interact with the history. I've long since expelled it from my brain, so that I can focus on the current state of the codebase. "5 commits ago, did you mean to do that, or can we take this other change?" I don't care, I don't want to think about it.

Of course, this issue can be reduced by the "squash first, then rebase" approach. Or judicious use of "git commit --amend --no-edit" to reduce the number of commits in my branch, therefore making the rebase less of a hassle. That's fine. But what if I didn't do that? I don't want my tools to judge me for my workflow. A user-friendly tool should non-judgmentally accommodate whatever convenient workflow I adopted in the past.

Git says, "oops, you screwed up by creating 50 lazy commits, now you need to put in 20 minutes figuring out how to cleverly combine them into 3 commits, before you can pull from main!" then I'm going to respond, "screw you, I will do the next-best easier alternative". I don't have time for the judgement.

Almost none of this is true.

Labor protections are indeed less, but this is actually a good thing. Like with many free-market topics, "labor protections" are a very dangerous thing, because they are a policy that sounds extremely good to the voting public, but many economists can tell you it's actually bad. US just got lucky, that it tricked the public to vote against it.

> and all other metrics that could somehow quantify quality of life vs purely financial terms

If you have measures in non-financial terms, I'm happy to consider those, as long as they have to do with labor market regulations.

> most jobs I had in Europe had a 1-3 months notice period which was easily negotiated if you really wanted to quit on the spot, no company wants to keep a disgruntled worker around

I could quibble that 1-3 months sounds like a shockingly long time from a US perspective, but the bigger problem is the "ease of finding a new job" part of the equation.

> making precarious conditions the default is not great for the less skilled people who prefer stability to keep their families afloat and secure.

The industries which don't experience as much instability are less likely to lay off people anyway. So workers who want stability can self-select into government jobs or something, which offer that stability.

> Not working in "innovation" still has the same precariousness, with no upside

Some industries are less precarious, I would say getting paid nearly twice as much is an upside.

> leave enough people behind and you get MAGA.

I don't think there's any strong evidence that income inequality caused maga. I couldn't find any evidence that poorer people are more likely to support Trump. But let me know if I'm wrong here.

> If “who is better off” isn’t a good question...

I said the American worker is better off in general. The only question I don't consider is good is, "which types of workers?" Unless your point is that some kinds of workers are better off than others? In which case, make that argument.

> “it doesn’t matter that you could be wrongfully imprisoned and separated from your children without recourse for committing no crime, but that’s OK because if it doesn’t happen you’ll make a bit more money” is detached from the reality of what matters.

You put that in quotes, but my comments have nothing whatsoever to do with that. Can you clarify what this has to do with whether a country should enact regulations which make it difficult for firms to lay off employees?

> Most individuals aren’t money-hungry ghouls who care for wealth above all, including their own personal safety and liberty.

Great. Again, what does this have to do with labor market regulations? I am not interested in debating "what matters" generally, in a "meaning of life" sort of way, unless you can connect it to labor market regulations, the discussion you entered.

I'm not interested in debating the grab-bag of ways life is better in Sweden than in California.

I've said this before, but every "US vs Europe work" debate ends with the European patronizingly scolding the American for thinking money is the most important thing in life. I'm also not interested in that.

I am only interested in the labor market.

You can say the numbers don't matter, but then you've adopted essentially an unfalsifiable position.

Another factor to consider is the ease of quitting your job. In the US (at least, I have found), it is quite easy to quite your job and find a new one.

This matches the logic under which it's easy to fire in the US. Every cost of a regulation has a side-effect. If it's easy to fire, it's easy to hire. The article explains how American companies are more willing to hire for positions which wouldn't otherwise exist.

If you are not interested in that, then quit your job and don't work in a position which involves innovation. Which in America, is easy to do.

I would argue that unemployment isn't solely about "money", but fair enough. I'm not sure how to respond overall. Because every time I debate this topic (which isn't a lot), a Europe defender will basically diminish the importance income numbers. Because "money is a poor measure of being better-off". In fact, money is quite a good measure of being better-off, and there is a lot of evidence for this. Europe has better public transportation, Europe has better healthcare, people are happier in Europe, etc etc... There is always more things. But the original discussion was specifically in the context of labor economics. Whether or not the US has single-player healthcare, that has a different topic. Average self-reported happiness numbers is obviously subjective and influenced by an infinitude of different things that are going on in one's life, which may or may not be related to labor. I also didn't find the other wikipedia articles very convincing. They show that ~2.0% of the US population is living below even the most generous measure of absolute poverty. I only see income inequality numbers as useful insofar as they give to average income number. I had cited median income so that the typical worker could be represented.

I don't consider "who is better off" to be a very good question. The answer is, the average worker is better off. My answer is therefore going to be vague. Of course, there are differences by industry, but do you have a point about that? Also, I am really arguing that with the current state of the USA, immigrants make higher incomes than immigrants to other countries. Saying that immigrants are treated poorly in other ways is just bringing up a political issue unrelated to labor economics.

> In what ways, specifically?

Median wages https://en.wikipedia.org/wiki/Median_income?useskin=vector Average work hours

Purchasing power parity https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(PPP)...

Despite average work hours https://en.wikipedia.org/wiki/List_of_countries_by_average_a...

Better youth unemployment than Europe https://en.wikipedia.org/wiki/List_of_countries_by_unemploym...

> And which types of workers?

High-skill professionals, entrepreneurs, specialized trades, creative workers, young people, immigrants... and most other professions.

> Can we skip the transparent rage bait and personal jabs, though?

If you make nebulous complaints about "shitting on workers" without considering tradeoffs, you've made a feelings-based argument, so expect that kind of rebuttal.

Are you not aware that this is the case? Look up affordability statistics.

It objectively is a negative. The American worker is much better off than the European worker. It doesn't matter if it makes you feel sad.

Why do you think software engineers in the US are paid twice as much as software engineers in Europe? Is it because US is better at crushing workers?

Honestly, the screw up was right there.

> When prices actually go down, builders get nervous, lenders get cautious, financing dries up, and projects disappear.

I think this is putting the cart before the horse. The entire reason that building/lending/etc should exist, it's raison d'être, is to make housing more affordable. If that is achieved - mission accomplished? I don't care about these parties otherwise.

Each of the terms used by the author, which I listed above, are fine and meaningful on their own. The problem is, it's jarring when academics try to shoehorn their pet issues into as many topics as possible, and combined with the raw density of academic verbiage, it gets quite grating. It tells you a lot about the sensibilities/priorities of the academic.

American universities are important institutions and do a lot of good work. However, look no further than this article for the source of the "white hot rage". It's bloviating, vacuous, empty fluff, no meaningful point or persuasive argument, and the statements which come the closest to resembling coherent points are wrong and bad (see https://www.danmcquillan.org/questions_for_anthropic.html). The author feels threatened, because he realizes that an AI could do his writing style much better than he does, given the absence of original thought.

The author is a kind of free-rider: he persists in his position having read just-enough continental philosophy, and memorized the right incantations (buzzwords) to communicate the "aligned" political subtext. Academic left-wing jargon; you have to be against neoliberalism, "tech broligarchy", Palantir (the military industrial complex), technogenesis... Oh, and you have to shoehorn as many race politics subjects into your article on AI, even if they have virtually nothing to do with the topic (KKK, White Genocide, racial superiority, supremacy, eugenics). Points for creativity, I guess.

Thank you. This author's writing is a careful exemplar of everything rotten about higher ed. The article is a great compilation of features, stylistic and material, that need to be crushed and discarded from the university.