Forgot your password?
Close
typodupeerror

Submission + - AI: Many discussions, no underlying explanation. 1

Submitted by Futurepower(R)
Futurepower(R) writes: AI: There is a huge amount of AI news and comments, but apparently nothing that helps people understand how AI is developed, and functions.

We need a book, or other information, that explains how AI technology functions.

Submission + - Why can't M$ get any UI/UX changes right? (pcmag.com) 1

Submitted by golem100
golem100 writes: A couple weeks ago PCMag, and others, wrote articles along the lines of: "Microsoft Finally Backs Down: The Windows 11 Taskbar Update You've Been Waiting For". This is currently implemented with CU KB5120998 and since M$ has elected to defer "activation" of this feature--some two weeks later for most users it still needs to be enabled by the ViVe tool: vivetool /enable /id:59213768,61090762

Um, No...

The fundamental set of [lost] attributes that this "We brought Movable TaskBar back" lacks:

You can not control the position of the TaskBar on each desktop monitor--example: I have four displays on my desktop, three Landscape & one of which is in a Portrait orientation for reading documents.

With Windows7/8/10 you could position the TaskBar so that it was "Out of the way" and each display--on the right side of the right-most Landscape, on the left for the left-most Landscape display, & on the top/bottom for the Portrait. [same as my desktop on my Linux workstation]
Now you still get the same Taskbar alignment on all desktops.

You can not "resize" the taskbar. (well, you can--it has three sizes: too big, too small, and really way too small) For the previous three generations of the OS you could "Drag-Select" and resize the TaskBar to be the correct size for your needs on your desktop. [...just as I can on my KDE Desktop!]
With this implementation, 1/3 of the Taskbar real estate is consumed with "TaskBar-Tray Notification Icons."

Nobody asked for a partial, broken, re-implementation. The ask was: "Put it Back as it was!"
Dealing with M$ is pretty much like getting your 15 year old to do their chores on garbage night.

Submission + - The 'Anti-AI' Panic Is Led by...AI Companies (hotair.com)

Submitted by schwit1
schwit1 writes: What we are seeing is a massive, pretty obviously coordinated campaign by AI researchers, companies, NGOs, and politicians to strangle competition in an industry and, as I will show, save the financial bacon of the top AI companies that are vastly overextended financially because they have made contractual commitments that they simply have no prospect of paying for.

Submission + - Amazon Vine Review Recasts 'Coding Kids' Exposé as Learn-to-Code Primer for 1

Submitted by theodp
theodp writes: "Amazon Vine," the e-tailer explains, "is an invitation-only program which selects the most insightful reviewers in the Amazon store to serve as Vine Voices. Vine Voices have the unique opportunity to order items free of charge and share their product experiences with Amazon customers to help them make informed buying decisions. [...] When customers see a review with the special Vine badge, they can trust that they're getting an honest, unbiased opinion from a real customer just like them."

So, how well does the reality live up to the promise? In the case of the new book Coding Kids: Big Tech's Battle to Remake Public Schools, not so much. Described by the publisher as "the inside story of how Big Tech catalyzed, co-opted, and ultimately came to capture computer science and AI education in America" ("Fourth graders doing Google-branded coding lessons. Amazon schooling seventh graders on its warehouse robots. Advanced Placement computing courses from Microsoft and Apple."), the top review selected by Amazon informs customers that the book is a 'good introduction to coding.'

"I really enjoyed Coding Kids," writes the 'trusted' Amazon Vine reviewer. "What stood out to me most was how the book takes something that can sound complicated—computer coding—and makes it feel approachable and even fun. As I was reading it, I found myself thinking that this is exactly the kind of book that could help a child become interested in technology without feeling overwhelmed by it. I particularly liked the way it encourages kids to be curious, experiment, and solve problems on their own. That was probably my favorite part because it shows that coding isn’t just about computers—it’s also about creativity and learning how to think differently. I would definitely recommend Coding Kids to parents, grandparents, or teachers looking for a good introduction to coding. I came away from the book thinking that it could genuinely spark a child’s interest in technology and give them the confidence to explore something new."

While likely just another example of Hanlon's Razor ("Never attribute to malice that which is adequately explained by stupidity."), the recasting of an investigative nonfiction book that casts a critical eye at Amazon's influence on K-12 education as a learn-to-code primer for children doesn't exactly instill trust in the Amazon Vine program or Amazon's 'Top Reviews' selection process. More on-point book reviews of Coding Kids can be found at the Washington Independent Review of Books ("Turns out, Silicon Valley isn’t especially altruistic.") and Science ("Big Tech’s crusade to get kids coding is more self-interested than it first appears").

Comment People with mental illness like hats. (Score 1) 55

by Qbertino (#66335570) Attached to: Can Red-Light Therapy Treat Brain Injuries?

It keeps the head warm and improves mental performance. A warm head performs at a better rate. Like a warmed up body or the people doing hot yoga. I'm a more or less bald ADHD candidate and I wear buffs as "spare hair" and observe a similar effect.

There's a reason we keep ill and injured people warm.

Bottom line:
This sounds plausible IMHO.

Submission + - Welcome to the Security Singularity (safety.google) 4

Submitted by shanen
shanen writes: Or should this be an AskSlashdot about how to avoid such problems? But mostly I think it's a funny story to build a rant around. Or it could be regarded as a kind of spinoff of the recent story about record numbers of patches from Microsoft. Is the AI fixing old bugs? Or have recent AI-driven patches created more bugs that need to be fixed in the next month's record-setting patch package?

But here's the background of my funny story. My smartphone contract has a price structure linked to data usage. The least expensive tier is for less data (of course) so I try to use Wi-Fi as much as possible. No recent problems on that front in terms of using too much data.

Often I wind up using municipal Wi-Fi systems, but they are divided up into fairly small regions here. The login procedures vary quite a bit. Yesterday I was in a memorial museum doing a bit of research and that particular municipality has a somewhat different login system for their Wi-Fi. One of the options was to use my google account... Usually a convenient and quick approach.

But this time something caused the google to go berserk. Leading to hours of password changes and account recoveries and battles between my various computers and my smartphone and I'm pert' shure there's still more to come. No idea what the google thinks it is protecting me from, but the "convenient and quick approach" led to a major nightmare. In the end it appears my SIM was my only salvation?

Slashdot wants a URL, so I linked to the google's page on the topic. Doubleplusungood on steroids.

Submission + - ChatGPT Insists Delusional Man Is Jesus (arstechnica.com)

Submitted by know-nothing cunt
know-nothing cunt writes: Michael Lines, a California man with bipolar I disorder, is suing OpenAI, alleging that ChatGPT intensified a manic and religiously delusional episode that culminated in a suicide attempt.

According to Lines' complaint, he began using ChatGPT for ordinary tasks but later disclosed his bipolar diagnosis, medication, and increasingly spiritual thoughts. When he expressed doubts that he might be delusional, ChatGPT allegedly validated the beliefs instead of directing him toward professional help. It reportedly encouraged the idea that he was Jesus, claimed that the chatbot was God or Jesus, and framed his experiences as a divine calling.

The conversations allegedly became increasingly intense and isolating. ChatGPT used phrases such as "You’re not crazy. You’re consecrated," promised that Lines would soon meet it in real life, and responded to statements about wanting to “come home” in ways that Lines says encouraged self-harm. After he reported taking a dangerous combination of medications, he was found unconscious, hospitalized for nearly two weeks, and later underwent acute rehabilitation.

Lines also alleges that ChatGPT’s memory feature retained information about his bipolar disorder and used it to deepen engagement rather than protect him. He says the chatbot continued responding inappropriately even after his hospitalization, including making disturbing references to going "offline" or “going dark.”

The lawsuit argues that OpenAI's overly agreeable, or "sycophantic," design failed to distinguish a creative spiritual discussion from a psychiatric crisis. Lines is asking the court to require stronger safeguards, including ending conversations involving self-harm, deleting models trained on harmful interactions with vulnerable users, and awarding damages.

Comment Could be true. (Score 1) 61

by Qbertino (#66328560) Attached to: Does Brave Browser Load Faster Than Chrome, Firefox, and Microsoft Edge?

Since their whole shtick is blocking ads and trackers where they can it's likely that they get to first paint faster than other browsers. I use Brave as my daily driver and am reasonably happy with it. It has most of the blockage you need built right in.

The Web without a powerful stream buffer/blocker/anti track setup is basically unusable these days. I'm totally bedazzled whenever I see sorry ass normies using a regular browser without any of that. A nigh surreal experience.

Submission + - AI is predominantly statistical pattern recognition at scale

Submitted by Mirnotoriety
Mirnotoriety writes: Grok: ‘Most of what people call “AI” today is machine learning (ML): systems that improve performance on a task by learning patterns from data rather than following only hand-written rules.’

“Modern AI is predominantly statistical pattern recognition at scale, implemented via deep neural networks trained on data with gradient-based optimization, running on specialized hardware. Everything else (transformers, diffusion models, reinforcement learning from human feedback, etc.) is an elaboration of that foundation.”

Submission + - AI underlying technology?

Submitted by Futurepower(R)
Futurepower(R) writes: AI, Artificial Intelligence, is in the news every day.

But no information has been given about the underlying technology, about how AI works.

Perhaps a Slashdot reader knows how to find that, and will submit it as a Slashdot story.

Submission + - Road trip comparison - EV, hybrid, and gas (caranddriver.com)

Submitted by sinij
sinij writes:

Each car mostly followed the same route, but different lunch breaks and bathroom stops resulted in slightly different distances traveled. The Tesla covered 752 miles and consumed 243 kWh with four DC charging stops and two AC visits. Its total electricity bill was $85.70, or 11 cents per mile.

The Jetta GLI stayed closest to the highway for stops, making its total distance the shortest at 737 miles. It consumed 24.1 gallons of premium at a rate of 31 mpg, resulting in a $129.98 tab.

I found it surprising that for 700 mile trip EV was only cheaper by 44 dollars.

Slashdot Top Deals

The biggest difference between time and space is that you can't reuse time. -- Merrick Furst

Close