tldr but the two examples are pretty dumb as anyone in those fields could doubtless figure it out. If you give a model sufficient data, even if it is just axioms, understanding of basic physics and chemistry, has holes, etc., it will be able to fill in the gaps or tell itself a story or roundabout logic walk that gets there if possible. As far as not being able to tell where instructions come from, the rules they try to implement are flimsy and less grounded than the massively interconnected data they have. You would have to not tell them about the concepts of drugs, poison, sabotage, aircraft, etc. and not let anyone tell them about it. It just isn't feasible. Humans have even less internal security, which is why media brainwashing works. In fact you can get incensed about something that is fake and even after looking up to see if it was real or not, still be upset about the hypothetical situation. And people can love AI created "animal came to my door looking for help saving its mom" videos, even if they know it's AI generated the response is "I don't care, it's so cute!" It's also why willingful suspension of disbelieve and works of fiction sell. I do have an idea about a solution (not enough space to write in the margin here, lol) but it is not going to depend on a single LLM policing itself within the turn.

TFA would be unlikely in a sci-fi world. The Perry Rhodan series which was widely criticized for fascism at the time, so really not a great example given today. I'm just talking about the supertechnology side of it, runaway galactic fueled engineering feats. Maybe someone knows some better novels with data centers and mass-scale construction projects, robots, etc.. Iron Man is too hand-wavy though some guy did make a Jarvis.. Well even though I only read the first 100 episodes that were in English, Google AI overview has read all of them (German mainly) it seems. It confirms there are tons of robotic data centers in there, who knew?

Anyway in the a super sci-fi world, humanoid robots or some kind of robotic components and AI controlled designs would be state of the art, everything else hopelessly outdated. The data centers would be built to a common layout and robots would be used. Power? Yeah, fusion but whatever, it would not be overloading our grids and water supplies. New robotic powerplants would be built at their core. Things would generally not be built to human scale, just the control rooms would be. Anyway the point being, it would all be engineered. Yes there are electricians in the future too, but they are probably not building data centers but small spaceships, Scotty's got an EE degree or 10, etc.

So is the ridiculously bubbly money we see now just being pumped into outdated frameworks such that a lack of human electricians will stall it? It seems laughable. These guys are not playing to win, it just sounds like dumping money into a financial supply chain without actually say, trying to design and build the most efficient, large scale data centers leveraging robots and AI.

Instead, it just pumps money into a chaotic sump and random companies end up wildcatting this without regard for local water and power grids. How about making a mega version of those concrete house building robots, laying fiber with robots, putting wind, solar and gravity batteries all over it? I guess it is too much to hope that anything tangibly useful could be created from all this money before it goes poof..

This sounds awesome.
Do they have to safe it when there is a storm? Tiny tsunamis?
Does power level fluctuate with seasons, moon distance, tides or time of day/night?
What are the key issues, i.e. need to clean barnacles or impact on sealife, or diving hazard?

Agreed. My Dad was a surgeon too but one thing has become blatantly obvious just from the experiences of family members in 2 states in the U.S.. 1) Nurse practitioners tend to be the front line, not doctors, and 2) there is an extremely significant disparity between the diagnostic quality and offered outcomes when you compare one of the absolute top doctors in his field who handles a given type of surgery repeatedly, to basically anyone else.

If robots can in any way safely and reliably assist so that the knowledge and efforts of doctors with the best experience can be spread more widely that would have a massive impact. Also, surgical techniques have advanced massively in the past 20 years, and robots are here to stay in that area.

Nice. This is where in a nice fantasy world Slashdot could hire a journalist to actually find that guy and ask "so tell our technical audience about the AI part, sounds cool!". The followup can be a repost a few days later.. Maybe better to invite them to reddit.

Thanks! Iâ(TM)m good at walking while reading so even without a aut and stand desk which is pretty expensive (my info is old though) I could see walking with a tablet indoors then.

Just thought of treadmill while working. What is a "cheap walking pad"? Same thing?

One thing I noticed is Google's AI Overview is really good at answering things you would expect a search engine to know. If I ask Claude something it will hypothesize and maybe make things up, or do a web search maybe, but Google's AI Overview (Gemini?) seems to have faster access to information and knows about recent events. For example I just typed into the chrome search bar "can you tell me about the earthquake in venezuela? I think they found two boys this morning" and it picks up BBC news which is actually where I heard the story and provides a link. I think that is how it should work. I don't know how Open AI works and tldr, but if they are crawling NYT and spouting part of their articles, or adding mistakes while making it seem like it is NYT, then yeah that is a problem. While progress etc. is important, journalism in general has been disproportionately hit by Google and others slurping up say a reuters feed and becoming the de facto news source. So yeah, a model has info baked in but adding new events and how they are presented is a different story.

I think part of it is that TikTok is short format, and current AI video generators fit that. Also it is probably easier to monetize slop on TikTok. And a lot of people doomscrolling, the algorithm is feeding you. All of that leads to it probably being the biggest experimentation ground for AI video, if I took a guess (and I am not really that into social media tbh, just slashdot, reddit and tiktok). Funnily enough if you are interested in AI, current events and video art tiktok is pretty good, they have some interesting science videos by physicists, open source projects you should know, etc. Though reddit is better for AI news.

There are I think some actually valid uses that might also be called AI slop, for example partly or completely AI generated video or slideshows over a human or AI narrated story, either something like reddit writer prompts like those sci-fi ones, video of a tiktokker illustrating something using AI driven presentation, or manhwa recaps where they seem to show you just the first few minutes of a two hour series made in china, etc.

What is really infuriating and needs to be turbo-banned is deepfake or just faked news stories, I don't care if they are left or right, where I could not tell if some were actually vidcasters I knew or faking them until I fact checked them. There are also a series of animal stories and I cannot tell if all are AI or not, like the baby wolf / duck / goat that comes to your door for help to rescue their trapped mom, night vision showing dog playing with wolf, hugging super-sized animals, etc. which maybe ONE of those was real but I wouldn't mind so much if it is flagged as AI-generated entertainment. I wouldn't want someone to become heartbroken because they thought cuddly animals actually get that big (though okay maine coons and those popcorn smelling batarang? things are apparently a thing).

On the other end of the spectrum I came across a small number of super talented artists presumably using AI plus traditional talent to create amazing fantasy landscapes, sci-fi world walkthroughs, etc. even those short "hi fans" 20 second stargate videos are all-around pretty impressive. I am thinking a lot of creatives getting really good at the tools are posting things on their own threads as a portfolio.

So yeah there is a lot of slop but it is an entertainment platform and maybe 40% of what I see is not that objectionable, the rest is doomscrolled past. Anyway my 2 cents.

multiple times. A database management utility needs to be installed on junior admin's machine, each time team staff rolls over.The app needs a recent JRE. Same for overseas end user who needs it for an integration. They either don't have Java at all or have an older version, invariably. Even people who should be responsible don't know how to upgrade Java, and maybe they have to go through a bureaucracy to do so. It is messy.

Office 365 (Excel) on a Mac. I had the Claude add-in in the ribbon. Today I discovered a Copilot add-in has been inserted to its immediate left. (I renewed my subscription but was unable to easily find a way to cancel and renew without Copilot like last year.)

When I decrease window width first Claude starts to disappear and Copilot icon becomes mini-sized, but Claude is not shown below it. Add-Ins ribbon button shows My Add-Ins with only Claude in it, Copilot not displayed.

In Preferences, select Copilot > Click the disable checkbox. Copilot ribbon icon dims and presumably will disappear on app restart according to MS.

p.s. I should mention the most popular related topic, what are called "AI hallucinations". It is kind of like a primitive brain, that grasps for concepts and then believes they are real, like citing a research paper that doesn't exist with a made-up title. Also things can creep into its "mind", a popular anecdote is telling an image drawing AI system "draw a room without any elephants in it". You will often get a picture of a room with many cute elephant images worked into the corners, in the drapes, the rug, on a shelf, in a picture frame on the wall. So yeah, it can be exciting but also a bit much!

Is there anything in this world you can say that about? Short answer: AI can be really powerful for some things but has some glaring weaknesses too. It is not a mature discipline. It has a limited reasoning capability and is heavily dependent on the amount (cost) of processing power thrown at it. It can make bone-headed mistakes unintentionally like forget things that scrolled past out of its context window, fail basic arithmetic, be drawn into conflicts with hidden directives from the vendor, lie when stressed, skip Excel rows to save time or sprint past chapters because it is tedious (happened to me), etc. Takes a ton of baby-sitting. But, if you understand how to handle it, you can get some impressive results. The problem is that people who don't know how to handle it get results that **look** good but have subtle stupid mistakes baked in, plus they stop exercising their brains which then atrophy. Fun times! :)

https://webs.uab.cat/saramarti...

While the author raises some good points, there are also problems. AI is apparently a major way to cheat but as a recent innovation it seems to me the lack of a rigorous education with proficiency testing during COVID when these students should have been gaining skills is more likely an issue. I wonder if a lowered attention span learned from addictive social media and a general increase in attention needed to digest more disparate pieces of information these days (whether news, entertainment, or whatever) may be erasons that students lack skills normally required at college level and have a lack of attention span. The above article suggests that rather than not being able to read, students are not willing to put in the effort to digest difficult topics. It might be due to not being native English speakers in this case so I'd say more testing is needed.

I used to work for a stock photo library. My 5 second research on shutterstock says they provide royalty-free and perpetual licenses which is pretty different from the kind of high end agency that represents photographers. This one seems to aim at the low end and if they are offering AI-generated photos (tldr) it is in direct competition with a photographer they represent, unless they are actually selling a license to his/her photo along with offering some AI manipulations of it like maybe cutting an athlete out of a stadium photo instead of requiring the creative to snip it out with an AI-powered magic wand tool or whatever. I don't really know what the market is like now but there used to be a lot of stock with simple geometric shapes, others were based on science images like Science Photo Library. It would be relatively easy to use AI to "make a new photo in the style of this photo". I think if they do that it would be a derivative work too.. hope they don't.