Automating the c-suite doesn’t save you money by cutting headcount, it saves you money by reducing salaries. Having a decently competent AI executive would put a lot of downward pressure on the insane benefits packages these folks get
Certainly. But in the current social environment, being seen as (mildly) careless is less bad than being seen as someone who lets an LLM write prose for them.
I make typos all the time as well, on stuff I am just writing off the cuff like a forum or chat message. But when it comes to something important, don't you check it over dozens of times? hundreds of times? A mere missing semicolon will make your code not compile. How could you let a superficial typo go uncorrected once you see it? How could you not see it when it's in the most obvious spot?
It suggests a certain lack of diligence; like you didn't proofread your work. What about the person that should have proofread it as a second opinion? Did this really follow a rigorous academic process at all? <- That's the first impression when the presentation is sloppy.
now they are exactly like every other company that has zero ethicists on staff and expect the employees to weigh the ethical ramifications of their work.
What companies do you think expect their employees to weigh the ethical ramifications of their work?
I’d argue a lot of them expect the opposite. To suppress the ethical concerns.
Even in recent memories you had Mark Zuckerberg telling his employees to use pirated sources. And executives at fossil fuel companies have to act unethically.
I think that individuals are capable of making ethical choices. I think that relying on individuals within for-profit businesses to make ethical decisions for the entire company is absolutely insane.
Food-testing: There's literally a parasite going around right now. Look at the response from some of the for profit businesses that was allowed to happen.
Hospitals: It is not ethical to deny patients care based on their insurance.
Clergy: The cover up of child sexual abuse scandals.
Childcare: lots of examples of sub-par care given to save money.
Those plans might work to give a nice sane internet experience to the folks that are willing to put in some money and effort.
But most people will still opt to stay on the slop-filled web because it’s free and because they like being angry. And as long as they stay the societal problems that stem from the toxic internet will live on.
I agree, it will filter for a certain kind of person, and most probably the people who are not a problem on today's Internet. If we cannot tamp down the filth that comes along with emphatic anonymity, then at least we can create some places without it. I'm getting to the point where I may pull the plug on my Internet as soon as I retire. Kinda hate to do that, because I remember when it didn't suck (at least not everywhere).
IMO once upon a time Facebook could have been that place, though maybe that ship has sailed now. There was a time when I thought they could choose to offer a premium experience for anyone willing to pay and there would have been a small but real subset of users who would go for it. Charge $25/mo (which I believe is approximately what they make off a normal US user) in return for zero ads, zero algorithm, complete control over the experience. Add another level above that which includes actively moderated members-only discussion forums.
always startling to see people discussing gwern with he/him because my mind defaults to assuming they're female because "gwern" scans a lot like "gwen"
i think there are a lot of college-educated folks that would love to switch into a trade, but there are cultural barriers to starting such a career. a not-insignificant number of tradespeople have been taught to see college as the enemy and college-educated folks as soft, coddled people with poor work ethic. if you showed up at a job site after getting a four-year liberal arts degree, you'd be met with lots of mocking and "oh, you thnk you're better than me?" defensive posturing.
i think major federal funding agencies should track department-level stats on "how many phd students did you admit?" versus "how many tenure track positions did you hire?" and use that to implement mechanisms that encourage a healthier balance (e.g., changing funding lines on grants, adjusting their overhead cuts, boosting trainee grants at certain places).
this would hopefully stop departments from over-admitting and encourage less adjunctification.
I’d love if there were different “layers” of meta discussion on top of everything on the web. Every blog and website would have an untold number of communities having discussions that are completely optional for you to view.
Instead of browsing across sites, you’d be browsing across communities seeing the same site.
I started working towards this goal in the latest release: you can now add Reddit as a source, so now when you visit a URL it will check across all subreddits where it's been posted and give you a blended discussion made up from everyone's comments.
I've been working towards building out functionality close to what you're describing. As a first feature, I added annotations where the script looks for HN comments quoting parts of the article and adds a highlighter effect. It lets you instantly see what parts of the text people are actually interested in. It's still a rough beta, but I'm actively working toward that exact vision.
the twenty-four hour news cycle's unyielding need for urgent content has broken many people psychologically and we need to 'deprogram' them.
i've often thought about making a site that lets you easily do side-by-side comparisons of news sites on different timescales (1 week, 1 month, 1 year) so you can pull it up and show them "see all this stuff that you feel like you NEED to consume? like it makes you a better informed member of society? how much of it actually mattered and how much of it was just there to hook you in the moment?"
I just wanna throw in that Tangle News[0] strikes a pretty good balance here. Their core offering is detailed breakdowns of what is generally regarded as the top four stories of the week, one a day from Monday through Thursday, which is usually more than enough space to keep you "up on current events", and they usually (though not always) tend to give enough space to let stories develop before summarizing.
The objective here feels like a good candidate for people to vibecode into their homebrew rss readers, in a composite feed. The marked source feeds then get hidden behind a minor effort gate. You still keep your unmarked and “safe” xkcd or whatever feeds as siblings.
A well informed population is important. The problem is they're not well informed they're well-hooked to whatever exaggeration and drama the news can whip up.
The invented news and invented intensity is the problem.
our brightest phds are attacking attention from all fronts (ads, social media, news), but the news one in particular is particularly insidious because for years you were told that watching the news made you a good, responsible person. but back then the news was just one or two 30minute blocks on TV and the newspaper.
People that get sucked into social media srolling for hours know that they're not doing something good for themselves, people are guzzling from the fear-monger newshose and they think they're doing something "healthy".
“ but back then the news was just one or two 30minute blocks on TV and the newspaper.”
There was all kinds of quasi-serious news-adjacent crap like 60 minutes, 48 hours, etc. The big difference was none if it was data driven and backed by algorithms that are constantly tuned for max engagement.
that is really interesting idea. I'd be really happy to read such a site, as I very often wonder if current hype/prediction will be relevant in the future. But I always forget to check being flooded by more hype.
reply