I just looked into this out of idle curiosity, after watching some guy build a LEGO sorting machine. (They work in a warehouse that sells used bricks for model builders.)
Interestingly, this is on the cusp of viability, but training the ML model would still be cost-prohibitive (for me). With $17M, it's within reach, but there's still the obvious mechanical hurdles: Kids don't disassemble their Lego, the conditions are "less than ideal", and even vibrating belts in a warehouse scenario have a lot of trouble keeping bricks separated for the camera to get a clear image.
Robot hands are nowhere near the point where they can reliably (or even unreliably!) take apart two arbitrary Lego bricks that are joined, let alone anything of even mild complexity. This is hard for most humans, and often requires the use of tools! See: https://www.lego.com/en-us/service/help-topics/article/lego-...
The machine vision part is... getting there! You could pull some clever tricks with modern hardware such as bright LED lights, multi-spectral or even hyper-spectral sensors, etc. The algorithms have improved a lot also. Early attempts could only recognise a few dozen distinct shapes, and the most recent models a few hundred, but they're about 2-3 years old, which means "stone ages".
A trick several Lego recognition model training runs used was to photo realistically render 3D models of bricks in random orientations and every possible color, which is far faster than manually labelling photos of real bricks.
These days you could use the NVIDIA Omniverse libraries to heavily accelerate and automate this.
As a meta activity, I like to run different codebases through the same bug-hunt prompt and compare the number found as a barometer of quality.
I was very impressed when the top three AIs all failed to find anything other than minor stylistic nitpicks in a huge blob of what to me looked like “spaghetti code” in LLVM.
Meanwhile at $dayjob the AI reviews all start with “This looks like someone’s failed attempt at…”
The BBC article in no shape, way, or form supports your statement that the school was "triple tapped".
The article was written by an Iranian, but let's just for a moment assume that they're not monumentally biased and instead let's look at the pictures and the text.
The picture in the BBC article clearly shows one impact point in the middle of the school building, and also one each in the surrounding IRGC buildings.
What "eyewitnesses" would have observed from some distance away would have been a series of explosions. Six to eight bombs, all dropped in rapid succession, likely from two to four planes.
Double-tapping (or triple tapping) involves a long delay between the initial hit and the follow-up hit. The idea being to also kill the emergency services personel that turn up... half an hour later.
The article carefully misquotes the locals who witnessed a series of explosions to suggest that this was a series of attacks on the school itself, but fails to scrape together the evidence to sell this narrative:
"suggesting it was hit more than once" -- but not proving. Actually, not showing that at all, since the picture clearly shows one hit on the building!
"around the Shajareh Tayebeh primary school" -- but not in the school.
"the area was "struck by multiple" -- the area around the school is an IRGC base, not "more school".
"Two damaged buildings" -- and then they admit one is the IRGC building leaving... one school building that was hit, once.
"difficult to independently verify" -- here the BBC admits to repeating IRGC propaganda without even bother to check the picture they put in their own article that obviously contradicts their biased narrative.
"speculation about what the intended target" -- what speculation? It was the IRGC base! It was a former IRGC building! Nobody in their right mind would "speculate" about this. This is a brazen lie.
"may have been used"
"who may have been operating"
etc...
I could keep on going, but why bother? This BBC article is total garbage, packed with deceptive language, weasel words, and "just asking questions".
The real, factually true heinous act here is the sloppiness of the US administration in keeping up with the changing status of IRGC targets. They got lazy, killed a 168 students and teachers, which is horrific.
We can blame them for their hubris. We can blame them for starting the war in the first place. We can lay the blame at their feet for any number of things.
But please don't repeat a made-up story of unbelievable, cartoonish evil. It's obvious that the US administration didn't set out to on-purpose kill school children! It's obvious that they didn't "double tap" the school building! It's obvious that they thought that they were hitting an IRGC building and it turned out not to be so. They made a mistake, but a mistake surrounded by deliberate war. Be angry at them starting this unnecessary war, which they did on purpose.
Why is it so hard to accept the basic fact that Iran - and Palestine (and China, and Russia, and Cuba, and ...) do not allow free press or free communication? That means with rare exceptions (unless someone is willing to risk their life for it) you ONLY have access to propaganda.
In any society that doesn't allow free press:
ANY television broadcast = government propaganda
Red Cross/Crescent = disguised government propaganda (Hamas/Iran's islamist regime)
ANY internet message = disguised government propaganda
ANY story published in the BBC with sources from that country = disguised government propaganda
ANY information delivered by anyone who wasn't risking their lives = disguised government propaganda
ANY information delivered by a foreign journalist "invited" into the country (ie. CNN in this conflict) = government propaganda (like "embedded journalists" in US army)
You do not have ANY information from within Iran except propaganda and very rare, very incomplete viewpoints (slowly) anonymously smuggled out. That's it. Yes, this means you generally just do not know. Not even if "the Red Cross/Crescent" says so, because they cannot risk saying anything but the government's viewpoint.
I get that this is very hard to understand for someone living in the US or Europe but that's how it is.
This was the case in the cold war with all the communist regimes. This is currently the case with Russia. With Cuba. With China. And, of course, with Iran. There is no information BUT propaganda from both sides. Nothing but that.
And sorry to point out the obvious, but given the choice between the US army and Iran's mullahs ... even Trump beats the islamist mullahs in reliability and credibility. Yes this is choosing the best option between Syfilis and Gonorrhea. But Trump wins that contest. Easily. Hands down.
I've experienced a nearly identical scenario where a large fleet of identical servers (Citrix session hosts) were crashing at a "rate" high enough that I had to "scale up" my crash dump collection scripts with automated analysis, distribution into about a hundred buckets, and then per-bucket statistical analysis of the variables. I had to compress, archive, and then simply throw away crash dumps because I had too many.
It was pure insanity, the crashes were variously caused by things like network drivers so old and vulnerable that "drive by" network scans by malware would BSOD the servers. Alternatively, successful virus infections would BSOD the servers because the viruses were written for desktop editions of Windows and couldn't handle the differences in the server edition, so they'd just crash the system. On and on. It was a shambling zombie horde, not a server farm.
I was made to jump through flaming hoops backwards to prove beyond a shadow of a doubt that every single individual critical Microsoft security patch a) definitely fixed one of the crash bugs and b) didn't break any apps.
I did so! I demonstrated a 3x improvement in overall performance -- which by itself is staggering -- and that BSODs dropped by a factor of hundreds. I had pages written up on each and every patch, specifically calling out how they precisely matched a bucket of BSODs exactly. I tested the apps. I showed that some of them that were broken before suddenly started working. I did extensive UAT, etc.
"No." was the firm answer from management.
"Too dangerous! Something could break! You don't know what these patches could do!" etc, etc. The arguments were pure insanity, totally illogical, counter to all available evidence, and motived only by animal fear. These people had been burned before, and they're never touching the stove again, or even going into the kitchen.
You cannot fix an organisation like this "from below" as an IC, or even a mid-level manager. CEOs would have a hard time turning a ship like this around. Heads would have to roll, all the way up to CIO, before anything could possibly be fixed.
The better analogy is that they ran out of the kitchen in a panic, and left the pots on the burners. Some time later there is smoke curling up from under the kitchen door, but they’re used to the burning smell by now so it’s “not that big a deal”.
I don’t know why you’re being voted down for stating plain facts.
If you know someone in town that regularly threatens you and your friends with death[1] and you see them buying a gun, you do something about it before they also get the bullets.
Iran has been steadily decreasing their “breakout time” to levels that Israel and the US considered unacceptable. Timelines too short to police with diplomacy.
They forced the hand of the Western world, they and their supporters are crying crocodile tears.
“We were just innocently enriching near weapons grade Uranium in underground facilities hardened against attack and inspection! Calm down bro!”
[1] To stretch the analogy further: they regularly hand out knives to their cousins, all of whom have stabbed your friend in a dark alley once or twice, to the point that your friend has to wear body armor at all times.
The JCPOA kept Iran from developing nuclear weapons. It was only the abrogation of this agreement by Trump which led Iran to resume enrichment of uranium.
Every marketing page and just about every second documentation page goes on and on about how fantastic CosmosDB performance and scalability is. Meanwhile, the best performance I have ever managed to squeeze out of it could be generously classified as "glacial".
Whenever I read its docs I feel like I'm being gaslit.
15 commits on Day #1 starting from an stub/empty repo. 47K lines of code developed in under two weeks by one person.
Sigh... AI slop.
reply