Yes, this is a key step when working with an agent—if they're able to check their work, they can iterate pretty quickly. If you're in the loop, something is wrong.
I'm trying to understand why this comment got downvoted. My best guess is that "if you're in the loop, something is wrong" is interpreted as there should be no human involvement at all.
The loop here, imo, refers to the feedback loop. And it's true that ideally there should be no human involvement there. A tight feedback loop is as important for llms as it is for humans. The more automated you make it, the better.
Yes, maybe I goofed on the phrasing. If you're in the feedback loop, something is wrong. Obviously a human should be "in the loop" in the sense that they're aware of and reviewing what the agent is doing.
This is super cool! I would be curious to see how Gemini 3 fares… I've found it to be even more effective than Opus 4.5 at technical analysis (in another domain).
Throughout time, people have complained that technology is ruining the world. Before AI it was the internet, and before that it was TV, nuclear power, and so on.
The quoted GP in the headline is correct. Life is just stressful. Previous generations understood this more, but my peers (Millennials) have an annoying tendency to complain that things are worse now than they ever have been, and their ADHD/anxiety is related to how "the world is now." It's BS. And it robs them of agency. Constant "happiness" should not be the goal, and the successful people Millennials admire are all living with stress and anxiety. It is normal.
> Throughout time, people have complained that technology is ruining the world. Before AI it was the internet, and before that it was TV, nuclear power, and so on.
What if throughout time they have been right ? Any proof thst while tech brought longer lifes and more material wealth, we haven’t just spiraled down for a while in term of mental wellbeing, sense of meaning, sense of belonging etc ?
That’s obviously not true of every piece of tech (I.e. it’s hard to imagine how antibiotics or replacing a coal plant by a nuclear power plant could have negative impact of people’s mental wellbeing) but it could be true about technology in general. It’s not a stretch to believe that technologies that radically transform what a day in the life of a human being looks like, can also have an impact on said human beings life.
Our bodies and mind, have been finetuned for living in nature and hunting gathering, with a small group consisting of our families and friends for millions of years. Now we live a sedentary life, for many away from family and without any sense of community, in large, noisy, devoid of nature cities having to do day in day out the same job that is more and more compartimentalized and less and less concrete and meaningful, only to go home and sit in front of a tv to be bombarded by ads trying to induce fomo, or god forbid, doom scrolling on tik tok for hours.
If it just so happened that those two modes of life generate the exact same levels and qualities of stress in our little brains, that would be quite the coincidence.
Look at every stat around mental health: anxiety, depression, sense of meaning etc. They are all getting worse over decades. And if you think it’s caused by people just complaining more than before, look at how the rate of people willing to kill themselves, that’s the ultimate truth. All worsening.
If you continue this argument ad infinitum, you'll eventually conclude that agriculture was our first mistake, and we should have just stayed in the cave.
Like, how is this line of reasoning constructive?
I guarantee our hunter-gatherer ancestors felt all the same emotions—burnout, comparison, envy, anxiety, stress, overwhelm, hopelessness. The setting has changed, but our brains have not changed that much.
> I guarantee our hunter-gatherer ancestors felt all the same emotions—burnout, comparison, envy, anxiety, stress, overwhelm, hopelessness.
Yes they felt all the same emotions. You absolutely cannot guarantee they felt them in the same proportions thought.
> our brains have not changed that much.
That is the point: our brains have not changed and is still evolving at the speed of gene mutations. Our environment though is changing magnitudes faster than before.
> how is this line of reasoning constructive?
This is not trying to be constructive, just trying to understand the human condition. We probably have no choice but to learn to deal with it, that doesn’t mean technology has no adverse impact.
Friend, hunter-gatherers felt more existential dread than you do, because 50% of their kids died, and they themselves would be lucky to live to the ripe old age of 40.
Every generation in history has felt that things used to be better and they got the short end of the stick. My grandparents lived through the Great Depression and World War II. My parents lived through the cold war, Watergate and Vietnam. Millennials have phones that they like too much, and it's slightly harder to buy a house, and they feel like no one has ever endured this much hardship.
We need to grow up. "Too much Instagram" is not remotely on the same level as "we need to hide in the basement during air raids."
PS, I don't buy any argument that there's more depression now than there was at an earlier point in history, because psychology does not have the most stellar track record when it comes to scientific rigor. I just don't trust any measure that's over 20 years old.
Sure, I'ld rather be doomscrolling on tiktok than being stuck for 4 years in trenches in France during WW1, we are talking about larger trend across time though.
> I just don't trust any measure that's over 20 years old.
Then take psychological measures that are 20 years old or less, they all go in the same direction.
Or if you don't trust psychology, take suicide rate, pretty hard to miscount, and is not subject to much change in how people self-report whether or not they killed themselves.
You seem to be conflating how you think people ought to feel given their privileged conditions versus how they actually happen to feel.
The case fatality ratio for measles infected children in high-income countries is also low. Nonetheless, we vaccinate children for this infectious disease because morbidity is also bad.
The Covid deaths were measured in thousands before they could find a single individual under 18 yrs old who died from it. The only reason to vaccinate kids was to try to prevent them from spreading it to adults. Right from the beginning (eg. With the cruise ship that was infected), it was extremely obvious that the main factor in survivability was age. The younger you were, the safer it was. Weight was also very important but we learned that later
Considering there have been over 7 million deaths directly from covid, saying "covid deaths measured in the thousands before X" is another way of saying "X happened right at the beginning of covid".
Plus, there's a big difference between "young people tend to have less risk of death" and "young people have a 0% chance of death" like the person I replied to claimed.
No, we also vaccinate children to prevent non-fatal illness, which is a reasonable choice to make if adverse effects of the vaccine are very small (they are). People get flu shots annually for this same reason.
Edit: I would also add that parents regularly make choices for their children that involve larger amounts of risk.
If they like money, they'll just roll HBO into Netflix and raise prices. I really doubt Disney's complex bundling/pricing scheme is helping their bottom line.
It also underlines in the US that sports is probably the last interest in linear programming. It would be interesting to get a picture of how many US customers will pay for ESPN in a Disney+ bundle but not Linear Hulu. I'm sure Disney will be tracking it, and probably made a smart move making the more interesting bundle the one with ESPN but not Linear Hulu.
There's a huge interest in sports in the US (and elsewhere). And broadcast rights reflect that. But there are also a bunch of people who would happily take a discount on all their other video to not include sports.
And sports coverage is very regional. Disney plus shows African football matches in S. Africa but in the US, I wouldn’t be surprised if it focused only on US football and US college teams.
In the US, ESPN somewhat built its reputation on having some of "all" sports, in part because when the channel started it was much easier/cheaper to fill 24 hours a day on cable with imports and non-traditional sports.
That still seems to mostly apply. In the US on Disney+ the US sports are often front and center, sure, but you can still scroll the list and get European football matches and some Aussie Rules Rugby and Cricket all kinds of things that people don't necessarily think US sports fans would watch. I think part of what ESPN realized, too, is that even regional sports can have global appeal with the right marketing or the fact that not much else is being played in that moment.
ESPN is also still often the home in the US of things like the Scripps National Spelling Bee and various Poker and Chess championships. This was famously mocked in the comedy movie Dodgeball with that movie's climactic Dodgeball championship happening on ESPN Ocho, the fictional 8th cable channel for US ESPN (which had 3 channels at the time). That joke has come full circle in interesting ways as ESPN has roughly 7 cable channels today and intentionally uses the "ESPN Ocho" branding for weirder/smaller audience championships even though the number of people that still remember the comedy movie Dodgeball is shrinking and people don't remember why it was a joke.
There are a few American sports fan who get up at 9am on a Saturday morning to watch the Premier League but that comes with an unbundled and affordable Peacock subscription. I used to be one of those guys but these days I might go to multiple games at my Uni and the other college in town and a weekend so I'm not inclined to watch sports on TV. Peacock has some other primo international sports such as the Rugby World Cup.
Yeah, it's interesting to watch which US streamers are adding which sports (that don't already have ESPN deals). Apple made a big deal about their MLS deal. Paramount+ has some random CBS Sports now. HBO Max has some sort of sports, I don't remember which.
I don't have cable or Disney+ any longer but, as someone who played rugby in school and still have an occasional interest, I find it's difficult to find in the US on TV.
I dunno about that. They introduced the ad supported tier as a way to reach consumers at a lower price point and apparently it’s been very successful. I don’t think they want to lose those customers by jacking up prices now.
Netflix has raised prices about 25% at the premium tier since they released the ad-free version in 2022. The with-ads plan has also seen increases since launch.
Their prices have been inching up. I pay for the lowest non-ad tier, and it's $17.99/mo. If I wanted 4K & HDR, it's up to $24.99/mo. At $7.99/mo for the ad-supported tier, they could easily bump that to $9.99/mo if it included HBO/Hulu/ESPN.
I’m pretty sure I would riot if they raise prices more. I’m not paying $30 to one streaming service. Criterion and Kanopy are working great for me as is.
I suspect you are right, but I’m not alone in walking away from this trend.
They lost me as a longtime customer after too many price hikes and low programming quality.
Netflix shows are “have it on in the background” quality whereas HBO has released some of the best TV of all time. This merger has enshittification written all over it.
I agree, but HBO has also gone downhill as they lost talent to other services. Currently the streamer with the highest consistent quality is Apple, which is pretty unexpected.
Apple has the benefit of the original Netflix exclusives model (and the original TV primetime distribution model) that they don't operate their own studios and instead can pick and choose from the cream of the crop of the more expensive projects from the others. (Severance is from Ben Stiller's Red Hour mini-studio, Ted Lasso and Shrinking are from WB Television, Slow Horses and Pluribus are from Sony Television, Foundation and Murderbot are from Skydance/Paramount Television, and so forth.)
I'm sure Apple is contributing significantly to many of those shows' budgets and helping them all reach similar quality bars, but Apple is also certainly benefiting from spreading that budget across multiple studios and not putting all their risk in (micro-)managing their own studio. Whereas a lot of the "streamer X has gone downhill" seems to be directly related to being able to source projects only from sibliing studios creating very simple monocultures of every project feeling the same and risking that bad or unlucky projects tainting other projects in that monoculture stew.
Very hit or miss though. And withs some exceptions like Slow Horses, their productions feel overly produced, oiled by agency crossover and 360 package deals, i.e., manufactured from script to screen. Even Pluribus has that smug sanitized gloss.
Honestly, in these days when pretty much everything is sourced from individual production companies and showrunners, it becomes pretty clear that while some studios have their own brands/budgets/priorities/execs/etc. there's no magic formula to getting it all right. It's been tried before and will be tried again.
In locations where fiber is not available (like my place), cable is the next best option, and cable has a lot more unexpected downtime. I could see this being a good backup, especially for small businesses like retail shops that couldn't afford to have their POS go down for half a day.
Agreed retail is a good customer for this tech. But even after getting fiber personally, it gets cut a lot by landscaping crews. Most of the time it’s a residential line that takes a day to fix. But a few times it’s been a main line and it takes 3-4 days. Maybe I’m unusual but that’s been my experience
Around here, it’s Starlink >> Fiber >> Cable because our lines are above ground and outages are frequent.
Fiber is less expensive than and more than 10x faster than starlink, in fairness.
Our 5g towers seem to run off the fiber lines, so it’s not really a backup (and gets overwhelmed anyway).
I’m considering getting fiber in addition to starlink, but I wish they’d just buried the lines.
I see telephone trucks repairing downed lines we’d rely on many dozens of times a year. Digging a trench would probably pay for itself in a year or two.
> Digging a trench would probably pay for itself in a year or two.
I know some people running independent community fiber ISPs. Digging trenches can be a nightmare depending on the neighbourhood. You can have property ownership issues, other utilities being present, permit nightmares, different ground/soil types, etc. That ignores the fact that when somebody else digs they can hit your lines and repairing that is a pain.
Digging is better, though. But it’s not necessarily as easy as one may think.
Where I work just acquired new property and are deploying a new site. It took 9 months, from date of first contact, before the ISP could come out, bore under the road, and run fiber to our building from two poles away. And that's just a short ~500 feet underground run.
I couldn't imagine the amount of permitting and logistics involved in trying to bury an entire run across town.
My community did the big dig around 2001. They finished around 2010. It was a huge project that took hundreds if not thousands of man-hours. I'm not sure if anyone ever actually calculated the total cost. And this is for a pretty small town. Now the day-to-day connectivity is much better, and weather almost never knocks us out, but when something does get knocked out, it takes longer to fix.
Overall, it's much nicer. No ugly telephone poles, don't have to worry about weather, just reliable, strong service. But to think it pays for itself in 2 years is laughable.
If you can't find a use for AI, you probably haven't given it much of a try. Just one random example: I needed to find experts in a technical field, and gave the problem to Claude Code. Claude put together a comprehensive research plan, dug deep into industry working groups, and produced a prioritized list of experts along with their bios, rationale and LinkedIn profiles.
Completely possible for me to do, but it saved me at least a couple hours of Googling.
Not quite but close. Titanic, like a lot of movies of the 90s and 2000s, was shot in Super 35. In Super 35, the image is ~4:3, but it requires optical printing or scanning to produce a release print, since the image is both not the correct aspect ratio and also occupies the area used for optical sound.
So it was not "cropped in the theater"—the theater got a standard anamorphic print. To go from the Super 35 negative to the anamorphic print, they both cropped and optically squeezed the image (in the case of the non-vfx shots), and scanned, cropped, squeezed digitally and printed back to film (in the case of the vfx shots). This was a few years before they did full "digital intermediates."
But once your DMARC, DKIM & SPF is configured correctly, there should be no reason for an MTA to reject your mail due to DMARC, right? I have DMARC reporting turned on, but am considering turning it off.
Back when I ran email for a large sender, I turned DMARC reports off once I got things settled in, and might turn it on to debug issues.
There was nothing to do about the reports most of the time. Just get mad that people are accepting spoofed mail that fails DKIM and SPF.
But mostly, the phishing campaigns with our branding just stopped spoofing addresses. Turns out, lots of email clients don't show the sender address and people who get a phishing email about Service Y from info@johnsplumbingservices.example.com may get phished.
That said, I love this project. haha
reply