So one of the problems with automated #translation based on #AI is that it's in this weird, awkward place now where it's not good enough to seem native, but it is good enough not to be immediately obvious. I had forgotten I set my browser to automatically translate pages in several languages to English for me. Then I clicked on a #fanfic, read the first couple chapters, and was getting really annoyed why one character kept changing Gender's, and the name of a location wasn't consistent from chapter to chapter. Turns out the author was writing in #Spanish, I hadn't noticed the language tag, and when I clicked the browser just automatically translated without clearly telling me. Thank goodness I realized, just in time, before I posted a comment on her work pointing out the issues with writing quality and offering editing help! Yikes! That doesn't mean that I'm against Machine Translation or even think it's a bad thing. But as it gets better and better, and starts living in this awkward uncanny valley, we really need to carefully rethink user interfaces. Maybe disable all form inputs until the user clicks "I'm aware this was translated" somewhere? I had the comment all written, folks; I was that close to posting. Maybe put "translated from" in some obvious place like the title bar? I don't know what the answer is, but I do know that we need to be putting way more thought into it.

@gutenberg_org For René Descartes, #AI would stand for ‘#ArtificialIdiot.’

#MATH

A growing number of people have come to rely on generative AI to do their work. Consider this a public service announcement: Make sure you double/triple check the output. @Futurism tells us about the police officers who learned this lesson like so many others have:

https://flip.it/U1.g6l

#Tech #AI #Technology #ArtificialIntelligence

From @WIRED: The U.S. invaded Venezuela and captured Nicolás Maduro. ChatGPT’s output delivered something else. Read more on how some AI chatbots have a surprisingly good handle on breaking news, while others don’t:

https://flip.it/yVnxfx

#Tech #ChatGPT #AI #Technology #ArtificialIntelligence

RE: https://hub.netzgemeinde.eu/display/451d2f06-7746-4227-a043-76a959420c29

(6/6)

#Long #LongPost #CWLong #CWLongPost #QuotePost #QuoteTweet #QuoteToot #QuoteBoost #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVA #AIVsHuman #HumanVsAI

The AI of my choice was LLaVA 1.6: https://llava.hliu.cc/

The prompt was, "Describe the image in detail."

LLaVA took about half a minute to generate this image description:

The image depicts a modern architectural structure with a distinctive design. The building features a large, curved roof that appears to be made of a reflective material, possibly glass or polished metal. The roof is supported by several tall, slender columns that are evenly spaced and rise from the ground to the roof's edge. The structure has a circular emblem on the front, which includes a stylized letter 'M' and a series of concentric circles, suggesting it might be a logo or emblem of some sort.

The building is situated on a landscaped area with a well-maintained lawn and a few trees. There is a paved walkway leading up to the entrance of the building, which is not visible in the image. The sky is clear with a few scattered clouds, indicating fair weather conditions. The overall style of the image is a digital rendering or a photograph of a 3D model, as indicated by the smooth surfaces and the absence of any visible texture or imperfections that would be present in a real-world photograph. There are no visible texts or brands that provide additional context about the building's purpose or location.

(5/6)

#Long #LongPost #CWLong #CWLongPost #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVA #AIVsHuman #HumanVsAI

This is the image I'm talking about: https://hub.netzgemeinde.eu/photos/jupiter_rowland/image/b1e7bf9c-07d8-45b6-90bb-f43e27199295 (linked instead of embedded so I don't have to go through the hassle of having to describe it right here right now).

This is the thread in which I've posted the image before, including image descriptions, also including a comment with the AI description and an analysis of the AI description in comparison with my own descriptions: https://hub.netzgemeinde.eu/item/f8ac991d-b64b-4290-be69-28feb51ba2a7 (yes, this is part of the Fediverse; it's on the same Hubzilla channel that I'm commenting from right now).

(2/6)

#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #AltTextMeta #CWAltTextMeta #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #AIVsHuman #HumanVsAI

However, I'm always at an unfair advantage. My images are renderings from very obscure 3-D virtual worlds. LLMs know next to nothing or actually nothing about these worlds whereas I dare say I'm an expert on them. An AI couldn't even tell whether the image is from a game or from a virtual world, much less which virtual world. I can not only exactly pinpoint where the image was taken (which place on which sim in which grid), but also explain the location and these virtual worlds in general.

Besides, an AI would describe the image by examining the image. I describe my images by going in-world and looking at the real deal instead of at the image of it. I can see everything at a vastly higher resolution. I can transcribe text that is so tiny in the image that it's invisible. I can even look around obstacles and see what's behind them if necessary. No LLM AI can do any of this.

(1/6)

#Long #LongPost #CWLong #CWLongPost #AltText #AltTextMeta #CWAltTextMeta #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #AIVsHuman #HumanVsAI

"In automation theory, a 'centaur' is a person who is assisted by a machine. You're a human head being carried around on a tireless robot body. Driving a car makes you a centaur, and so does using autocomplete. And obviously, a reverse centaur is a machine head on a human body, a person who is serving as a squishy meat appendage for an uncaring machine." Start the New Year right by reading the transcript of @pluralistic's lecture for the University of Washington, a preview of his upcoming book about his thoughts on AI, and how to be a good AI critic. "AI is the asbestos in the walls of our technological society, stuffed there with wild abandon by a finance sector and tech monopolists run amok. We will be excavating it for a generation or more."

https://flip.it/B1emjI

#Technology #Tech #ArtificialIntelligence #AI #CoryDoctorow

More concerns over content manipulation and online safety. CNBC reports: “Elon Musk’s Grok chatbot blamed “lapses in safeguards” for the recent posting of artificial intelligence-generated sexualized pictures of children in response to user questions.” Read more, including Musk’s response:

https://flip.it/GLVjn4

#Tech #AI #Grok #Technology #Internet #ArtificialIntelligence

Meet the new tech laws of 2026.

@theverge reports: "Coming into force this year: AI regulations galore, a teen social media lockdown, and 'Taylor Swift' laws."

https://flip.it/zmw6ea

#Tech #Technology #AI #2026

Playing around with Antigravity, vibe coded a social media summarizer that makes a summary of the last 48 hours of my bluesky and mastodon timelines, using python, a local database of the posts on my laptop and APIs of mentioned services. Works greats after squashing some bugs and a few iterations. Interestingly you need to know a little bit about coding to use it efficienctly, even in "vibecode" mode.
#AI #Antigravity #Google #vibecoding

Alt...

My vibecoded app that summarizes my mastodon and bluesky timelines

It could have stopped at 'Most likely to Argue', but I'll take the differentiation.

🤬https://philosophics.blog/2026/01/02/a-year-of-chatgpt-2025/?utm_source=linkedin&utm_medium=social

A blog post about ChatGPT's year in review. I sent over 35K messages to ChatGPT, and it's only one of 8 GPTs I use – though it is ichiban.

#blog #chatgpt #gpts #ai #philosophy #whimsy #yearend #newyear #novelty #chat #agency

Alt...

cake

This year, #Odysee will be integrating OneTrust into their platform for efficient AI governance. They don’t want the platform to become an AI slop dumping ground.

Source: Trust me bro

https://www.onetrust.com/

#AI #Aislop

Archaeologists use AI to bring prehistoric life to interactive video games

Archaeologists in Scandinavia are showing how new advances in artificial intelligence and free game development software could change how the public encounters the distant past...

More information: https://archaeologymag.com/2025/12/archaeologists-use-ai-for-interactive-video-games/

Follow us @archaeology

#archaeology #archeology #archaeologynews #AI #neolithic

Alt...

Archaeologists use AI to bring prehistoric life to interactive video games

The early-bird deadline for #NISOPlus26 in Baltimore is just two weeks away!

Start the new year off right & register by Jan 14 for the best rates—then join us to help brainstorm solutions to big challenges in #ScholComm: https://niso.plus/niso-plus-2026-baltimore/

#metadata #AI #ResearchIntegrity #OpenResearch #standards

Alt...

NISO Plus Baltimore 2026 with Baltimore skyline. February 16–18, Marriott Waterfront, Register Now! https://niso.plus

We asked a humanoid robot if there is an AI bubble. Here’s what it said.

From CNBC: https://flip.it/4kK42r

#AI #ArtificialIntelligence #Tech #Technology

Does Meta's $2 billion acquisition of AI startup Manus make sense?

Analysis from @mg: https://flip.it/I4sCWR

#Meta #Manu #AI #ArtificialIntelligence #Technology

Pearl v0.1.11 is out! This is a big update because it finally adds prompt switching. As you talk, Pearl will change her tone based on the context of the conversation. This also sets the stage for a lot of customization down the road. #ai #coding #pearl #python

Check it out! https://github.com/pdschneider/Pearl/releases/tag/v0.1.11

This year I accomplished a lot, and it was exhausting. Join me as I appreciate what I was able to do and reassess my time management: https://writerofminds.blogspot.com/2025/12/year-in-review-2025.html
#AI #robotics #writingCommunity

Alt...

Art of a flock of brown birds (swallows, perhaps) swooping up from the lower left. A single bird has gotten ahead of the the flock and appears about to touch a sun-like fiery globe in the upper right corner. The background is abstract; the birds are leaving a swooping gray wake on the left side, pale blue clouds surround the sun, and the rest of the scene is a flat light blue or white.

Sometimes smart homes fall short of expectations. In 2025, with the arrival of generative AI assistants, there was a bumper crop of snafus. PC World ranks the biggest smart home fails, from overheating beds roasting sleepers to privacy-infringing toilet cams:

https://flip.it/KPAU87

#Tech #Smarthome #AI #Technology #ArtificialIntelligence #Home

💻 AI is now the norm in software development, but security hasn’t caught up.

This blog explains:
• Why productivity is driving #AI adoption
• Where AI-generated code creates real security risk
• What developers need to watch out for

Read Part 1:
https://openssf.org/blog/2025/12/29/ai-software-development-security-tips-and-the-future-part-1/

#NISOPlus26 in Baltimore is **the** place to explore solutions to some of the most pressing challenges in #ScholComm!

Join us to participate in the conversations that lead to new projects & initiatives around #AI, #ResearchIntegrity, #OpenResearch infrastructure, & more. Early bird deadline is January 14, & there are discounts for NISO members & groups: https://niso.plus/niso-plus-2026-baltimore/

Alt...

NISO Plus Baltimore 2026 with Baltimore skyline. February 16–18, Marriott Waterfront, Register Now! https://niso.plus

That's Late Stage Capitalism for you:

"More than 20% of the videos that YouTube’s algorithm shows to new users are “AI slop” – low-quality AI-generated content designed to farm views, research has found.

The video-editing company Kapwing surveyed 15,000 of the world’s most popular YouTube channels – the top 100 in every country – and found that 278 of them contain only AI slop.

Together, these AI slop channels have amassed more than 63bn views and 221 million subscribers, generating about $117m (£90m) in revenue each year, according to estimates.

The researchers also made a new YouTube account and found that 104 of the first 500 videos recommended to its feed were AI slop. One-third of the 500 videos were “brainrot”, a category that includes AI slop and other low-quality content made to monetise attention.

The findings are a snapshot of a rapidly expanding industry that is saturating big social media platforms – from X to Meta to YouTube – and defining a new era of content: decontextualised, addictive and international.

A Guardian analysis this year found that nearly 10% of YouTube’s fastest-growing channels were AI slop, racking up millions of views despite the platform’s efforts to curb “inauthentic content”."

https://www.theguardian.com/technology/2025/dec/27/more-than-20-of-videos-shown-to-new-youtube-users-are-ai-slop-study-finds

#AI #GenerativeAI #GeneratedVideos #AISlop #YouTube

Pearl v0.1.10 is out!

This version lets you attach files to messages so Pearl can help you with to-do lists, meal planning, #coding, and more! It also feature general usability improvements. #AI #FOSS

Download on #Github: https://github.com/pdschneider/Pearl/releases/tag/v0.1.10

#Privacy #AI #Singularity

AI is not the future of anything except domination and control. AI is the death of the future and the return to a dark age of conformity and social thought control. AI regurgitates accepted dogma and is a bar to real research and inspired creativity. AI is a homogeneity engine.

People becoming dependent upon AI will be homogenized zombies. Of course the AI will convince them they are wise thinkers. The more obedient they are to their hidden masters, the black box owners, the more the singularity system will assure them they are the avant garde of gray matter.

I have already seen numerous instances of idiots depending upon AI to come up with ridiculous conclusions while defending them like Don Qixote. This is becoming epidemic among researchers and techies.

Watch out for the controlled opposition--public figures pretending to be against creeping enslavement while leading their followers to do absolutely nothing useful to curtail or stop the advance.

#AI #ArtificialIntelligence #Singularity #Tech

Why not listen to @tanakian 's stream today instead: https://toobnix.org/w/cVxKX6WZCLBHNzrw4NiWMq

#lispyGopherClimate Sunday-morning-in-Europe #peertube LIVE .

Short show. #archive https://toobnix.org/w/rzDtsQPUf4Kudrq4xZCAy9

https://toobnix.org/w/gXLXQqxf5MYg1NDF2Ua6oA

No gremlins (hopefully).

Just #eev #git and #slime #commonLisp #elisp useage. Then I am going to compare #ai to https://en.wikipedia.org/wiki/Blast_fishing and changes since #gof_ai .

Also! I am going to be away for the following two weeks, sorry about the unscheduled downtime.

Alt...

The Halloween Lispy Gopher Show banner. The lisp alien has a very long neck (and many terrifying eyes). The gopher looks on, concerned.

@nixCraft I told the actual human at customer service on the phone to tell corporate to shove their worthless fucking AI “helper” up their collective asses and then I asked her to make sure and sign my name. LOL #AI

Has anyone read the new NIST AI bits? I built a chatbot test plan, worth aligning with NIST likely.

https://www.infosecurity-magazine.com/news/nist-mitre-ai-centers/

#ai #pentesting

The Linux Foundation’s 2025 Annual Report highlights growth across AI, global standards, security, education, and community participation.
Here are the main takeaways from this year’s report.
Link:https://www.linuxfoundation.org/resources/publications/linux-foundation-annual-report-2025?hsLang=en
#OpenSource #FOSS #LF2025 #AI #Security #OpenStandards #Collaboration

@plantarum

I mean air Canada had to uphold the deal their AI chat bot did on their behalf, so there is precedent for AI content to be considered official content from a corp.

#libel #AI #Google

Strong 2025 vibes #MagnusRobotFighter #HappyHolidays #AI #BetterLuckNextYear

Alt...

A man in a shot pink onesie and white boots karate chops the head off of a wiggly armed robot in a 70s comic book. The text reads "these perfect servants had become the masters of men and only through the incredible powers of Magnus could the human race be saved!"

I know a guy who spent hours playing the stock market during the dot-com boom. He invested in every buzz word company in the news. He became a millionaire!

On paper. In December.

Then came the crash, and he couldn't sell. He lost everything. Wiped out.

The IRS came calling to collect taxes on all of his dot-com wealth from the year before. Well, he said, I'm wiped out! Too bad, they said, you owe us for that year. Pay up!

They were brutal.

Say, kids, how many of you are invested in AI or crypto in December, 2025?

#AI #crypto

BBC: AI app apologises over false crime alerts across US

A company behind an AI-powered app called CrimeRadar has apologised for the distress caused by false crime alerts issued to local US communities after a BBC Verify investigation.

CrimeRadar uses artificial intelligence to monitor openly available police radio communications, automatically generating a transcript and then producing crime alerts for users across the US.

BBC Verify has found multiple instances from Florida to Oregon of CrimeRadar sending misleading and inaccurate alerts about serious crime to local residents - as Thomas Copeland explains.

https://www.bbc.com/news/videos/c4g4v3yd28yo

#AI #alerts #crime