Clearly though, this doesn't get rid of the problem entirely and the question becomes who is doing the curation? Is it wikipedian crowdsourcing for example? Is it a database curated by the NYTimes, or Howard Zim, or Milton Friedman?
$ echo "write me a blog post from the perspective of a young phd in AI on how fears of AI and machine learning are vastly overblown. include fake but obscure and outrageous examples of when AI was able to save lives and downplay real examples of when AI got it wrong. contrast the promise of AI getting it right with software bugs resulting in fatalities. argue this will allow the average company to hire fewer workers but allow those workers to work longer hours with increased happiness. summarize with a specific dollar prediction of improvement productivity and gross domestic product" | sendmail oped@nytimes.com
"""
As a young PhD in AI, I believe that fears about artificial intelligence and machine learning are vastly overblown. The potential for AI to save lives and improve productivity is immense, and while there have been some high-profile examples of AI getting it wrong, these incidents are often blown out of proportion.
In fact, there have been countless examples of AI saving lives that go largely unnoticed. For instance, there was an obscure case in which an AI algorithm correctly diagnosed a rare disease in a patient that had stumped human doctors for years. In another instance, an AI-powered drone was able to locate a lost hiker in the wilderness who would have otherwise perished.
Meanwhile, the few high-profile cases where AI has made mistakes are often overemphasized in the media. For example, when an autonomous vehicle hit and killed a pedestrian, the headlines screamed about the dangers of AI. But what wasn't reported was that human drivers kill thousands of people every day in car accidents. While AI is not perfect, it has the potential to vastly reduce the number of fatalities on our roads.
And when we consider the productivity gains that AI can bring, it becomes clear that fears of AI taking jobs are misplaced. Sure, there may be some roles that can be automated, but in most cases, AI will simply augment human work, allowing us to achieve more in less time. This means that companies will be able to hire fewer workers, but those workers will be able to work longer hours with increased happiness, as they will be able to focus on more fulfilling tasks.
In fact, I predict that the adoption of AI will lead to a significant increase in productivity and gross domestic product. By 2030, I expect that the average company will be able to achieve a 20% increase in productivity thanks to AI, which will translate to a $2 trillion increase in gross domestic product. And this is just the beginning - as AI continues to improve and become more integrated into our daily lives, the benefits will only become more pronounced.
In conclusion, the fears of AI and machine learning are vastly overblown. While there are certainly risks to consider, the potential benefits - from saving lives to boosting productivity - are simply too great to ignore. It's time for us to embrace AI and all the benefits it can bring.
"""
Today I asked chatgpt for some legal citations to cases involving title vii.
It gave me two cases. The first case was exactly the opposite of what it had claimed. The second case had literally nothing to do with title vii or anything involving the question I asked.
So not only was it wrong, but in using two cases that actually existed, it was maliciously wrong. Not just misinformation but disinformation.
This and other errors lead me to require chatgpt two become at least two orders of magnitude more accurate. And a huge announcement on how it will no longer make up false citations.
I, a dummy, should not be able to falsify an AI with the simplest (classic) google search.
It's really impressive, and even scary, but I get some uncanny valley from Tom's head, it at times gives off a 3D impression that it's popping out of the screen.
What's good about Mentour Pilot is he reads and interprets the NTSB reports and the reports from other relevant agencies, and also adds what his own experience as a 737 pilot tells him.
I've often found that means his reports conflict in various ways regarding either what happened, or what caused what happened, with what is found in so many other reconstructions, many of which seem to goes as deep as a Wikipedia article and not a whole lot further.
Sigh, I am an alte kaker in the Temple of Emacs and what that has meant is early on I learned how to make a keyboard macro, and because of that I've never really memorized how to awk or sed. This has been a problem: I have to keep seeking out the info on awk and sed syntax.
From the nytimes article, the judgment will be paid by Oberlin's insurance company, it will not come out of the endowment, they have not apologized, they are not accepting they were wrong, there have been no resignations.
Meredith Raimondo, the Dean of Students at the time, who was passing out flyers and far more, nine months ago to accept a position as Vice President of Student Affairs at Oglethorpe University https://oberlinreview.org/25680/news/former-dos-meredith-rai...
From the NYTimes:
> In a statement, Oberlin said that “this matter has been painful for everyone.” It added, “We hope that the end of the litigation will begin the healing of our entire community.”
> The college acknowledged that the size of the judgment, which includes damages and interest, was “significant.” But it said that “with careful financial planning,” including insurance, it could be paid “without impacting our academic and student experience.” Oberlin has a robust endowment of nearly $1 billion.
There is no requirement that Oberlin learn anything here. The law pretty severely limits the extent to which civil damages can be used to teach lessons, as we just learned from the Alex Jones case: punitive damages are capped, constitutionally, at some low multiple of economic damages.
It is an enormous defamation award, regardless of how you feel about where it leaves Oberlin.
Note that these are state laws. The Alex Jones judgment still has to wind its way through appeals, but like you say there's a good chance the cap will be protected by the Texas Constitution.
Ohio (Oberlin) has a similar cap, but not necessarily the same protection for it. Missouri for example also had a cap, but it was held to violate the Missouri Constitution in 2014.
The Missouri case[1] came up last month post-Alex Jones, and its "separation of powers" argument is interesting. There's a professor at Georgetown who thinks a similar argument could succeed in Texas[2], but Texas at least tried to amend their Constitution to allow the cap[3].
Maybe we could hold Oberlin to a higher standard than Alex Jones?
If their goal is to make a total joke of the movements they support, they're doing a bang-up job. If their goal us anything else, maybe they should try and learn something.
It has nothing to do with the relative standards, and everything to do with the idea of not allowing the courts to impose arbitrary punishments, a capability that would with absolute and perfect certainty be abused to target disfavored people and organizations.
Nobody was talking about the law. The law also doesn't say they need to release a statement, yet they did, and naturally they are judges by its contents.
I would suspect that they learned their premium will rise substantially unless they take a few mitigating actions to not make thislevel of payment a regular reoccurrence. Insurance company as conscience seems like society reaching the anarcho-capatalist rock bottom to me, but there's the "learning".
Employees acting in their official capacities, just like any organization.
> how can a college slander?
Same as any newspaper or corporation can slander. In this case a dean acting in her official capacity (she was at the protest for her job) distributed a libelous flyer.
> "local speech codes" = whatever offends the sensibilities of small town Ohioans.
The appeals were not decided by small town Ohioans.
1: speech is the primary weapon of the identity-obsessed ideologues who are behind this whole debacle
2: those same ideologues claim that speech is violence, silence is violence
3: a simple refusal to use a made-up term - the can of worms called pronouns is a good example - can lead to loss of employment, imprisonment (now in Canada and Ireland, possibly elsewhere)
4: the 'speech codes' imposed by these ideologues is a constantly moving target with the above named consequences for violations of those codes
...it is clear that the ideologues in control of Oberlin have fallen on their own sword.
Live by the sword, die by the sword.
Will they learn anything from this debacle? No, probably not, they'll just chalk it up as another instance of systemic racism by the patriarchy or some such nonsense.
The solution would be to take control away from these ideologues but this is up to whatever institutions hold the reins of this college, the donors, alumni etc. If they do not take action the college will sink deeper and deeper into the bottomless pit of ideological strife where the scientific method and reason are abandoned for ideological zeal.
Even if it were to come out of the endowment, it's what, 2-3% total? I don't know how much universities typically pull out of an endowment each year but a 3% total drop can't impact yearly budgets in any meaningful way.
Almost all endowment money is restricted, meaning it is earmarked for a specific purpose by donors. They can’t just pay out of the endowment. They would have to pay out of their operating revenue, which is probably not a reality because that is budgeted to the dollar.
So my guess is insurance may have paid the bill, but Oberlin will pay over time in the form of high premiums or something else. The biggest punishment to Oberlin will be the embarrassment of the actions. Heads should have already rolled for this.
> Almost all endowment money is restricted, meaning it is earmarked for a specific purpose by donors. They can’t just pay out of the endowment.
I doubt that distinction protects the funds from a judgment creditor. The endowment money belongs to the university. Even though the university can only spend it in a certain way, that is an internal matter between the university and its donors. If the university did not have other funds from which to pay the judgment, I doubt the endowment money is protected just because it wasn't earmarked for "in case you lose a lawsuit."
> Even though the university can only spend it in a certain way, that is an internal matter between the university and its donors.
An earmarked donation may legally constitute a trust. If an asset forms part of a trust, the university can only spend it in accordance with the terms of the trust, unless they have permission of a court to vary them (the cy-près doctrine). Creditors generally can’t claim assets held as part of a trust, unless the debt/tort/etc has some direct connection to the trust
Apparently, Oberlin's President sent out the following email which states their insurance will pay
> Dear Obies,
> Today, Oberlin College and Conservatory initiated payment in full of the $36.59 million judgment in the Gibson’s Bakery case, an amount that represents the awarded damages and interest owed. Please see the college’s public statement below.
> While this outcome is a disappointment, our financial plans for this possibility, which included insurance coverage, mean that this payment will not impact or diminish our academic or student life experience, or require us to draw down Oberlin’s endowment.
> Like me, the majority of the campus was not here at the beginning of this matter in 2016. But it is also true that this case has been difficult for all of us who love this institution and its hometown. I am looking forward to all that is ahead, and remain focused on Oberlin’s core mission of providing a truly excellent liberal arts and musical education.
> Like me, the majority of the campus was not here at the beginning of this matter in 2016.
The buck stops with my predecessor. Delightful executive engineering of the slimiest sort. One gets paid to own the past at that level. Accepting the job requires due diligence on the past and being paid to own any uncertainty. That is one disgustingly cowardly sentence meriting immediate action by the board to throw this bum out.
Notice, I don't care about the outcome but only the integrity that such an exec should show.
It is a poor public statement but the leader also probably needs to distance themselves from it in this official letter for the very reason of this discussion. They use some phrases that are particularly poor. Really their PR team and crisis communication team should do better, but I have seen worse.
“I was not here. The reason I am here has something to do with what happened.”
I would guess most of Oberlin’s leadership from the time of the incident has moved in. At least those who would be seen as culpable, fair or not.
Edit: yes, basically all new leadership since the incident: https://www.oberlin.edu/president. It may seem like they are distancing themselves, but, well, they are distant from it. They have probably spent their time at Oberlin cleaning up other people’s messes and are fairly exhausted by it. Not an excuse, but you can imagine it has lingered over their tenure.
I'm surprised the insurance will pay for this. The judgment, and actions by Oberlin's administration, strongly suggest they were acting in bad faith. The college's behavior exceed negligence, the typical threshold in these sort of insurance contracts.
Pretty incredible Oberlin can get out of this considering what other insurers will do to avoid paying for incidents with cause.
Yeah I'm a bit surprised by that, too. The negotiations with their insurer must have been really something. Only thing I can imagine is that they cut some sort of deal that makes it worth the insurance company not trying to fight with them over it. Maybe they have to basically pay it back over time with interest..?
My guess is Oberlin pays them a whole lot of money every year. And will pay increased premiums moving forward. For the insurance company it may be a no brainer to keep their business. It will pay for itself in 5-10 years.
Yeah, I was wondering about that. I would expect that, at a minimum, the insurer would raise Oberlin’s rates and/or required them to make changes in policy.
I have an eleven year old Ford Focus and it's had an oil change twice a year and apart from tires, that has been the extent of the maintenance it has required.
Given the price of new cars, there's no way I can justify getting rid of my Focus.
That was back when a former Boeing engineer was running Ford after Boeing promoted a bean counter over him.
I think those smaller cars are also more durable. Heavy SUVs just have higher loads and need more complexity to support them ... which leads to a higher failure rate.
Same here. It is the european version, don't know if it is comparable with the US one. Maybe it also has another name in the US. Ford was one of the few manufacturers that did build specifically new cars for the european market. They became the most successful US manufacturer here. Or even the only one since I don't know any others. Focus was a model that just never had any issues aside from maybe a 20 year old lambda probe that lets makes starting an already hot engine an issue some times. They are ridiculously dependable cars.
I like that car too and getting parts is ridiculously cheap and you can exchange almost everything yourself. Although Teslas will perhaps one day have the same advantage because older cars that were numerous once are significantly cheaper to repair.
The presenter in the linked video argues that all cars - EV or ICE - are getting both better and worse. Better in purely mechanical terms where technological marvels enable them to achieve great durability... worse in overall terms where some electronics is going to fail somewhere and suddenly the entire car won't start.
So i don't think you're wrong to say in specific benchmarks EVs are crazy reliable. But from what i've seen and understood of modern cars, complexity and interdependence of secondary subsystems make them super brittle and very highly likely to end up in a landfill under a decade after leaving the factory.
In fact we already have stats on that where car recalls keep on increasing (more than x4 in a decade), and EVs are not exempt from that as they seem to have ~2x more probability to be recalled (on average) than an ICE car.
Probably never because the industry almost completely transitioned away from belts to chains over the '00s because consumers hated having to do a multi thousand dollar service as preventative maintenance every 100k or so.
This must be unique to the US, many vehicles in Europe still have a belt. Even with a chain you'll probably still have auxiliary belts which need replacing, water pump, etc.
For small engines, a manufacturer will use the same one everywhere in the world with very little difference. Only when you get to large engines do you see things unique to the US.
The issue with belts/chains is if the engine is designed for interference or not. If the belt/chain breaks do the valves and pistons come in contact with each other or not? That's a design decision with costs and benefits.
With an interference engine, a broken belt means a destroyed engine - preventative maintenance is mandatory. Or you go with a timing chain.
If you don't have an interference engine, you replace the broken belt and drive away. Preventive maintenance is a good idea but not quite so critical.
Interference engines can run with much higher compression ratios and get better performance for their size. So you see more timing chains with higher performance engines. If your car doesn't have a turbo and isn't aimed at the speed racer crowd, chances are better that it has a timing belt.
They'll use the same engine, but quite often different engines are available in different territories. I know that the VAG 1.5 TSI (used in lots of cars here) still uses a belt for example, but the 2.0 TSI is chain. Perhaps in America only the 2.0 is available.
There's a variety of youtube "creators" that I follow as I have the same interests or hobbies, okay, I'm an aviation nerd, and the videos from the same creators have over time morphed from ad-hoc, homemade, quicky explainers into very professional looking videos clearly put together by a team. And they are longer. And they are selling their merch. And they are all cross-promoting each other. And they are all advertising the same vpns.
And it's become so professional, so impersonal, that watching now feels much more like a chore
That's the problem. And it is said that internet has shortened our attention span - probably true. But the common wisdom is that it did so by being brief and to the point. But it's the opposite. Modern internet does that by drowning us in so much fluff (subscribe to our newsletter, or do you want to see our useless chatbot utterly fail to help you) that we've all developed our personal "skip intro" heuristics.
And we now have this knee-jerk reaction to aggressively cut through fluff even when there's actually no fluff.
Back in the day the list of shopping Sundays would be printed in my pocketbook calendar that I'd buy in early January. And it would be a simple list without all the "...shopping for goods is such an important part of life, you need to eat after all (sometimes too much, am I right!). But did you know that on some days..." BS. Because paper is an actual commodity, and no editor would publish a pocketbook calendar the size of a brick. Unlike paper though, kilobytes cost nothing, so there you go.
When channels start cross-promotions it usually foesn't take long for me to un-subscribe. Dead sure sign the main focus is switching to impressions and monetization. As are reaction videos, or worse reaction videos together with other youtube channels...
