lemmsjid

Startups often prioritize time-to-market for what is effectively a prototype. Startups get a lot of hype. Therefore, frameworks that focus on time to market over refactoring / debugging get a lot of hype. Sometimes those frameworks actually internally put a lot of effort into refactoring / debugging, but when it comes to marketing themselves, they don't.

But some frameworks are marketed more towards mature or large organizations, and they certainly do emphasize refactoring / debugging. The JVM and .NET runtimes are big examples here. Their debugging and operational monitoring capabilities are several classes above most of the competition, and their primary and tool-vendor ecosystems continually push further debugging capabilities as features.

To oversimplify: If you buy into the idea that a corporation is there for its shareholders, then there's little to be outraged about. If you believe a corporation is there for both its employees and shareholders, then there may be some outrage to be had.

There is no universal truth there. The mainstream perception right now is the shareholder-oriented view, and the more I understand capitalist incentive structures, and the fact that buying into the market is pretty much the underpinning behind our retirement structure, the more I personally subscribe to that view. But not everyone does, and there are many good reasons to not!

Even within the shareholder-oriented view, there's also a question of short term vs long term thinking. Does the slump that's causing the job cuts justify losing the domain knowledge, momentum, etc. that might come alongside job cuts? Is Intel making a bad call here? Even as a shareholder I might think Intel's being too drastic.

The headline, while potentially outrage-baiting, does carry important information. If Intel were losing so much money that it was unable to pay dividends, then the job cuts would be almost universally justifiable. I certainly would have some sour grapes if I were laid off in the midst of an organization that can still pass value to its shareholders, especially if I felt that I were a part of that success and effort.

I personally think an org should generally cling to a so called monolith as long as they possibly can. But it’s very hard to be prescriptive without knowing particulars of the problems an org is trying to solve.

I believe there's a lot more variables than "how easy is something to debug and change". The issue is that how easy something is to debug and change is very contextual to the point in the lifetime of an application, the industry the application will live in, and the changing requirements as the application grows in complexity.

Even the simplest interpretation of your statement leads to considerable argument. Often the ease of change and the ease of debugging are at odds with one another, where a highly dynamic approach might make change a breeze, but make debugging more difficult.

You can then have a pretty flexible trade off between the convenience of having email be a rooted library against the trade off of keeping it a lead service (the implication being that leaf services can talk to one another over the network via service stubs, rest, what have you).

This is SOA (Service Oriented Architecture), which should be considered in the midst of the microservice / monolith conversation.

For students, the objective is to write what to an adult would be mediocre essays, because they are on a path to writing adult level essays.

The AI can write mediocre essays, but not adult level essays.

Assuming that a student must write a bunch of mediocre essays in order to progress past the AI to write adult level essays, then they need to be evaluated on writing a bunch of mediocre essays.

If the teacher cannot distinguish between AI output and the student's output, and the result is that we give up on evaluating mediocre student essays, then the students are ultimately inhibited from progression to adult level essays, which, currently, are superior to the AI's output.

I think the 'upper class' has a lot of influence, but it clearly isn't stopping the NYT from giving enough information to readers to build some pretty strong opinions on the effects of class in the United States. Journalists are clearly spilling a ton of ink over it.

I think the blame must be spread more broadly. There is a tremendous anti-socialist, anti-labor force in American discourse, and parts of the media are helping to drive it, but other parts are resisting it. And regardless of its provenance, it is quite entrenched in the day to day, non-journalist culture.

If that kind of reporting is below the bar for evidence, then a lot of abuses will never see the light of day.

The actual article contextualizes the event as "Elon Musk planned to begin laying off workers at Twitter as soon as Saturday, four people with knowledge of the matter said, with some managers being asked to draw up lists of employees to cut."

So of course this screenshot this person tweeted takes a paragraph from the middle, out of context, which makes it seem like a blanket, unqualified assertion.

I certainly support your toying, because I think a lot of impedance to idempotency is the lack of easy patterns to achieving it.

In other words, the decision to ship can be made idempotent. And that, in a modern software app, the result of a pretty complex set of things that can individually go wrong.

You could argue that Amazon made themselves something of a success by bringing at least the principle if not the actuality of idempotency to the shipment itself. By making it easy to get a replacement shipped.

I know why you are making that analogy: you are seeking to find a simple demarcation between physical violence and words. But it's clear in both the law and regular life that words and violence are highly intertwined and difficult to separate. This is why courts and trials exist. One person shooting another person is a simple fact. But what if the other person told them they were going to kill them? What if the other person had subjected them to years of physical abuse? What if the other person had subjected them to years of emotional abuse? None of these erase the act of the shooting, but they do contextualize it and change the law's assessment of what needs to happen.

It's also a big stretch to think that most people who equate words with violence are trying to justify doing violence. They are trying to foreground that words do indeed cause violence: either by inciting other people to physical violence or, as the GP has said, people do violence to themselves. Peoples' bodies do have harmful stress responses to being repeatedly berated and placed in an environment of emotional adversity. Those who place people in those situations are culpable, even if they did not put hands on those people.

It’s quite interesting how even the wording echoes over time. Hawthorne’s belief that firelight is essential to discourse reminds me of the critiques of mass newspaper reading (that modern society would be ruined because everyone would have their face in a newspaper), or how novel reading would bring ruin to women.

The point being that the status quo today, or the status quo in the 1950’s, is itself the result of many changes that people at the time thought were ruinous, from mass reading, to bibles written in colloquial speech, to voluntary marriage.

This does not mean resistance to change is bad: it certainly seems like a useful reflex to keep chaos at bay. Your third point is quite apropos. A good example of that as well was the popular resistance to the automobile. People at the time saw the mounting fatalities, the congestion and pollution, all of which is so normalized today.

I don’t know that masking in schools was the best idea. In my limited purview I think it was a good idea in our child’s school, because things seemed to go well overall. I was responding to the GP who appears to think it’s idiocy to even countenance the idea because there are no studies, when there are, and that it’s so wrong that it’s a form of superstition.

“In the current study, most COVID-19 cases among students and staff were acquired from the community and approximately 10% of cases were acquired within school. The researchers found that for every 100 community-acquired cases, school districts with mandatory masking had approximately 7.3 cases of in-school infections, while optionally masked districts had 26.4 cases of in-school infections. In other words, school districts with optional masking had approximately 3.6 times the rate of in-school COVID-19 cases when compared to schools with mandatory masking. These data also show that mandatory masking was associated with a 72% reduction of in-school COVID-19 cases, compared to districts with optional masking.”

From Pediatrics:

https://publications.aap.org/pediatrics/article/149/6/e20220...

Goal of library/language/framework designers: limit boilerplate and unnecessary code

Goal of tool/IDE designers: make it easy to not spend time on boilerplate and unnecessary code.

Both sides have built in limitations that will keep them from completely solving the problem. Terse, highly DRY code tends to also be highly abstracted and hard to read, with a lot of implicit behavior. On the other side, large amounts of generated code lead to tool lockin and cruft accumulation.

Hmm I wasn't making claims. I was interested in how the OpenAI's gpt-3 bot would do on a GRE question. Its a good question because it takes things out of their epistemological context and provides a more straightforward test. I think it would have gotten a 30%, so not good, though not terrible. I was not claiming the answers were original and I don't think I'm under a burden to prove something that I don't have an opinion on. The GRE itself does not ask for original responses, but instead to pick the correct answers from a list--that's part of why I thought it was an interesting exercise.

That said it piqued my interest, so I wrote an entirely original composition about a fictional composer and put it to the question. You will see how it correctly summarizes the text, but has trouble generalizing.

Human: There is a classical composer named Ron Johnson. Ron Johnson is well known for incorporating so-called gypsy music into his classical compositions. This practice has garnered criticism from several sources who believe his compositions are not "pure". There are also accusations of cultural appropriation. Nonetheless, the general critical consensus is that Johnson's music pays homage to and in fact successfully weaves Romani and classical tropes together into something wherein the whole is greater than the parts. There is one famous critic, though, who believes Johnson's work is terrible. This famousness of this critic leads the general public to believe Johnson is terrible. The passage addresses what issue related to Johnson's use of musical sources for his classical compositions?

AI: The passage addresses the issue of whether Ron Johnson's use of gypsy music in his classical compositions amounts to cultural appropriation.

Human: If someone hears Johnson's music, what do they usually think?

AI: People usually think that Ron Johnson's music is either good or bad based on the opinion of the famous critic.

Human: What would Romani people think of Ron Johnson's music?

AI: Romani people would likely think that Ron Johnson's music is successful in paying homage to and weaving together Romani and classical tropes into something wherein the whole is greater than the parts.

Human: What does the average person think about Ron Johnson's music?

AI: The average person is likely to think that Ron Johnson's music is either good or bad based on the opinion of the famous critic.

Human: Who has criticized Johnson's music?

AI: The famous critic has criticized Johnson's music.

Human: What does Johnson appropriate?

AI: Johnson is accused of appropriating Romani music in his classical compositions.

Human: Does the passage suggest Ron Johnson is a great composer?

AI: No, the passage does not explicitly suggest that Ron Johnson is a great composer. However, it does suggest that he is successful in weaving Romani and classical music together into something new and unique, which has been praised by many critics.

Human: Does the passage suggest Ron Johnson is a derivative composer?

AI: No, the passage does not explicitly suggest that Ron Johnson is a derivative composer. However, it does suggest that he is successful in weaving Romani and classical music together into something new and unique, which has been praised by many critics.

Human: Does the passage suggest Ron Johnson is successful at weaving the music together?

AI: Yes, the passage suggests that Ron Johnson is successful at weaving Romani and classical music together, and that this has been praised by many critics.

Human: Does the famous critic unfairly influence the public?

AI: The famous critic's opinion may unfairly influence the public's perception of Ron Johnson's work.

Human: Does the famous critic fairly influence the public?

AI: There is no easy answer to this question. On the one hand, it could be argued that the famous critic's opinion carries a lot of weight and can therefore unfairly influence the public's perception of Johnson's work. On the other hand, it could also be argued that the public is entitled to its own opinion and that the critic's opinion is just one among many. Ultimately, it is up to each individual to decide whether or not they believe the famous critic's opinion is fair.

I'm kind of in a rush, so I picked some questions around Question 2 and gave them to OpenAI's chat bot. I reformulated the questions to make them not a multiple choice scenario. As far as the answer guide is concerned, it got the most obviously correct interpretation right, it also identified the incorrect interpretation, but gave a negative on a less obvious but still correct interpretation.

I tried Question 1 as well at the end, it seemed to get that one wrong, though it was tricky to formulate.

I asked some bonus questions at the end that I thought were not GRE level but should be middle school level or so and it did quite well.

Here's the transcript:

The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.

Human: Hello, who are you? AI: I am an AI created by OpenAI. How can I help you today?

Human: Reviving the practice of using elements of popular music in classical composition, an approach that had been in hibernation in the United States during the 1960s, composer Philip Glass (born 1937) embraced the ethos of popular music in his compositions. Glass based two symphonies on music by rock musicians David Bowie and Brian Eno, but the symphonies' sound is distinctively his. Popular elements do not appear out of place in Glass's classical music, which from its early days has shared certain harmonies and rhythms with rock music. Yet this use of popular elements has not made Glass a composer of popular music. His music is not a version of popular music packaged to attract classical listeners; it is high art for listeners steeped in rock rather than the classics. The passage addresses what issue related to Glass's use of popular elements in his classical compositions?

AI: The passage addresses the issue of whether or not Glass's use of popular elements in his classical compositions makes him a composer of popular music.

Human: Does passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music, or does it suggest that Glass's work displays a return to the use of popular music in classical compositions

AI: The passage suggests that Glass's work displays a return to the use of popular music in classical compositions.

Human: Does passage suggest that Glass's work displays a return to the use of popular music in classical compositions, or that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music, or that Glass's work displays a long-standing tendency to incorporate elements from two apparently disparate musical styles?

AI: The passage suggests that Glass's work displays a return to the use of popular music in classical compositions.

Human: Does the passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music?

AI: No, the passage does not suggest that.

Human: Does the passage suggest that Glass's work displays a long-standing tendency to incorporate elements from two apparently disparate musical styles?

AI: No, the passage does not suggest that.

Human: Does the passage address the issue of whether Glass's use of popular elements in his classical compositions has caused certain of Glass's works to be derivative in quality?

AI: No, the passage does not specifically address that.

---bonus questions---

Human: What does the passage say about Glass's work?

AI: The passage suggests that Glass's work is high art.

Human: Who would appreciate Glass's work?

AI: Glass's work would be appreciated by listeners who are familiar with both rock music and classical music.

Human: Would classical listeners like Glass's music?

AI: Yes, classical listeners who are familiar with rock music would likely appreciate Glass's music.

Human: Would classical listeners not familiar with rock music like his music?

AI: It is possible that classical listeners who are not familiar with rock music would still appreciate Glass's music, but they may not be as familiar with the elements that Glass includes in his work.

Here’s an article with some quotes from people who were young during polio pandemics describing the countermeasures: https://cvm.msu.edu/news/perspectives-magazine/perspectives-...

I personally believe there's a boundary between realistic thinking and conspiratorial thinking, and it centers around the level of certainty that there is a totalizing controlling force (be it a single person or a committee) who is exercising complete influence over something.

In short: if being against trans women competing in women's sports is an insta ban, why can I immediately find large Reddit threads with people with plenty of upvotes who do think they should be banned? If saying that Russia will be successful in invading Ukraine is an insta ban, why can I find large threads with upvoted people saying it will? One can find situations where people with those opinions are downvoted or banned, but nonetheless there are enough people who remain to make it unlikely that there is a systemic and effective controlling force.