#Google AI Overviews put people at risk of harm with misleading health advice - https://www.theguardian.com/technology/2026/jan/02/google-ai-overviews-risk-harm-misleading-health-information

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

Beloved family-owned #Cincinnati BBQ restaurant and food truck vender that was featured in a #Google #Gemini Super Bowl commercial last year is forced to sell food trucks amid financial challenges, now directing customers to order from her website vs 3rd party online ordering, their chicken thighs have skyrocketed from $30 per case in 2020 to $130 in May 2025

"In 2024, we did about 30% of the revenue that we had in years past," said Kristen Bailey, co-owner of Sweets and Meats BBQ.

She's now asking customers to call, or, if ordering online, order directly from her website, vs 3rd party online ordering due to the fees they collect #Ohio #TrumpsEconomy

https://www.wcpo.com/news/local-news/finding-solutions/family-owned-cincinnati-restaurant-forced-to-sell-food-truck-amid-financial-challenges

Being generous, I'd say that about half of #Google #Gemini responses have some error or misunderstanding in them that I can recognize. Something like 25% are completely wrong or totally miss the point. I have no idea how many responses there are that are actually wrong in some respect but I don't have the background knowledge to recognize any errors. USELESS.

@jti42 @pkal @ghul cuz I think that in the legal battle game #FLOSS vs. #Corporations that #OpenSource would be on the loosing end.

• The main success factor for #Linux is not only it's #licensing but also that it coopted #GAFAMs into being contributors that pay key #developers.

And since they all have stakes with partially diverging interests, this is a useful way to take their resources (personnel hours and money) for something good (instead of them wasting it on #Enshittification, #Cyberfascism and #Militarization)…

• IOW: Would you rather want some developer from #nvidia work on #Linux or #Palantir's #Govware? Cuz shure as hell said developer ain't gonna stop developing for 6 figures per year either way.

Kinda like @landley pointed out that #Android - unlike #iOS - is gonna be "salvageable" (and due to #Google going *full 'asshole mode' that #fork is necessary sooner than anticipated)…

• This is opportunistic af but that is kinda necessary until the world decides to ban capitalism, redistributes wealth and sentence billionaires to lifetime community service without parole.

#sarcasm #politricks

@ghul @jti42 @pkal @landley precisely!

Besides: All those big corpos contributing don't do so out of kindness either, but because none of them want to cough up way more money for a #CCSS alternative like Wind River #VxWorks, #Oracle #Solaris or god forbid #IBM #zArchitecture #Mainframes!

• #Android will need to have a #Community #Fork unless #Google instantly and retroactively revers their "#Developer #Verification" bs even for non-#GooglePlay #Apps!

@darryl_ramm
Like the 'old' motto of #google said: "don't be evil"
@molly0xfff

Monstrous AI Slop imitating famous people is OUT OF CONTROL on YouTube

It's a horrific scourge. Realistic AI imitations of celebrities, politicians, and more putting words in their mouths that they never said are flooding #YouTube. Sometimes the "Altered or synthetic content" label is visible if you bother to look at the description (which takes extra effort on YT TV interfaces in particular) but the similar warning banner that used to appear for some seconds overlaid on the videos no longer seems to routinely appear.

#Google is creating a monster, and sooner rather than later that monster is likely to turn on its maker.

@Tutanota

Some other simple things

8. Disable google advertising ID in phone settings

9. Install F-Droid where you can discover many FLOSS apps deliberately not published on google play

10. Switch from a fingerprint to a pin (added bonus that police in several countries can legally force your thumb onto your phone but cant legally force you to give up a pin)

11. Switch from google notification servers to something else like microg and/or set notifications to not display message content or at least not display message content when the phone is locked (Im pretty sure all that can be done from notification settings)

12. Switch from googles keyboard app to an open source alternative from f-droid (google has been fined millions before for illegally and secretly tracking geolocation it wouldnt surprise me if they do the same with keystrokes, and also mic and camera)

13. There's a bunch of other phone-home features spread across the settings but mostly under privacy category and accessibility category that you might want to turn off if you have no use for

#Google #Android #Privacy #PSA #FLOSS #FDroid #Advertising #Microg

Cybercriminals collected the credentials in #phishing campaigns targeting American citizens through fraudulent ads on Google and Bing search services that led to fake banking portals.

NOTE it says through ads served by #Google and #Bing.

The most important point in the article is, "... Online banking users are recommended to bookmark official banking portals instead of searching on Google or Bing or to use ad blockers that hide promoted results entirely".

Ad blockers are for security, regardless of what Google and others try to tell you. They are essential protection.

https://www.bleepingcomputer.com/news/security/fbi-seizes-domain-storing-bank-credentials-stolen-from-us-victims/

#Cybersecurity #Phishing #Scam

And I suppose the diminutive men in charge won't do anything about it until their daughters get stripped down as well.

Wired, from yesterday: Google’s and OpenAI’s Chatbots Can Strip Women in Photos Down to Bikinis https://www.wired.com/story/google-and-openais-chatbots-can-strip-women-in-photos-down-to-bikinis/ @WIRED #OpenAI #Google

@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

#Google AI confuses a musician with a child molester, and basically laughs it off like haha live with it!

Socket, from yesterday: Malicious Chrome Extensions “Phantom Shuttle” Masquerade as a VPN to Intercept Traffic and Exfiltrate Credentials https://socket.dev/blog/malicious-chrome-extensions-phantom-shuttle @SocketSecurity

More:

The Hacker News: https://thehackernews.com/2025/12/two-chrome-extensions-caught-secretly.html @thehackernews #infosec #Chrome #Google #VPN

So TalkBack 16.2 had an update that fixes the image button issue. It would call buttons with images just image, like the Back navigation button.

But it *still* has an issue where it replaces the Line up and Line down commands on the Humanware NLS EReader, a Braille display given out to blind people across the US, with D-pad up and D-pad down. The Humanware NLS EReader doesn't even have a D-pad. So there is no way to move up and down by line. This will hit more people in the TalkBack 16.2 rollout, and those with an NLS Ereader will see just how carefully Google cares about Braille. /s

And there's no way to change these Braille commands. So now if I want to skip a bunch of filter radio buttons in Audible and get to the first book, I have to go one item at a time for a good 10 elements until I find the first book. If I use another Braille display, the Braille Edge, which does have line up and line down mapped, those commands now only move by line *within* the currently selected item, not vertically down the screen. So even if those commands did work, it won't help.

Android just isn't ready for purely Braille access. And no I don't want to have to pull out my phone and tap the screen. I don't have to do that on iOS which is supposed to be the less customizable platform; why should I have to on Android?

Adding on to this the other issues like not being able to navigate threaded emails easily, moving from one message to the next in a conversation, the notification shade getting worse with "expanded" being replaced with "fully expanded" which is more screen reader clutter I have to listen to or read before hearing the actual notification, and the name of the app on a collapsed stack of notifications being replaced with just a number, and for me it doesn't matter how many Bluetooth keyboard commands there are if Braille support doesn't improve also. I don't use a Bluetooth keyboard. Maybe if I did I'd be happy. But I use Braille, and they should *also* be focusing on that.

We should be able to enter our PIN, hit modifier keys like Control + n for a new email in the Gmail app, or even open apps with our Braille displays, and the TalkBack Braille keyboard, without having to find and hit a search button, or install a custom launcher that may or may not work well for us. I mean Braille Access on iOS just plain works a good 80% of the time. and while image descriptions on Android are great, the Braille support is frustrating enough that, when I'm on Android, I hate using Braille. And that's really sad. Apple just helps us out a bit. Google leaves us to flounder around until we hit a good spot to where it "meets our needs", or is "*shrugs* good enough". They don't strive for excelence, just "good enough." And as Apple continues to advance, "good enough" ain't good enough anymore.

#technology #tech #apple #google #iOS #Android #accessibility #blind

#Google AI screws up again -- announces winner of football game hours before the actual game, complete with fake highlights

This AI Slime was obvious. But what of all the times it's NOT obvious
and can do SERIOUS DAMAGE? -L

https://www.msn.com/en-us/news/technology/google-app-hiccup-jumps-the-gun-before-the-eagles-commanders-game-with-ai-generated-victory-post/ar-AA1SKjv2

As an experiment, I tried using #Google Gemini's bananayammawhateverthehellit'scalled AI to create a simple test pattern with some text overlaid on it. After an hour of trying different prompts and updated prompts, with long waits between each as Google wasted more electricity, I finally gave up. Such a simple thing, and Google was utterly incapable of getting it right. I created the image manually with Gimp in 5 minutes. Generative AI is, essentially, a horrifically wasteful fraud, as it sucks up electricity, water, and now computer RAM driving its prices through the roof, all to enrich the Billionaire Big Tech CEOs with this AI Slime. The Billionaires ARE THE PROBLEM.

Reuters: Google Cloud lands deal with Palo Alto Networks 'approaching $10 billion,' per source https://www.reuters.com/business/google-cloud-lands-deal-with-palo-alto-networks-approaching-10-billion-per-2025-12-19/ @Reuters #Google #PaloAlto

Just give the Epstein files to Google and let them OCR and index them. #Google can do something useful for a change.

This is the script of my national radio report yesterday on the new #Google/Pentagon Partnership for #Gemini Military #AI. As always there may have been minor wording variations from this script as I presented the report live on air.

- - -

So yes, this has quickly turned into a rather strange Pentagon story but before we get further into it I want to answer a question I've seen posed frequently: Is it the Department of Defense or Department of War?

And this turns out to be a pretty easy one. Only Congress can change a name like that for legal or statutory purposes, and Congress has not done this. So the official legal name is still Department of Defense. An executive order created a secondary name which is Department of War, and that can be used in public communications and basically various other non-statutory contexts. It isn't clear how much has been spent changing various stuff to that secondary name, but apparently estimates are that to do total rebranding to Department of War would cost many billions of dollars and perhaps Congress doesn't want to rush into that. I have seen some references to Department of War as the "cosplay" name but I'm fine just saying the Pentagon so that's what I'll be using here today.

So as we know the Billionaire Big Tech CEOs want their AI in EVERYTHING, and Google apparently won a contract with the Pentagon to put a version of Google Gemini AI in front of several million U.S. armed forces members and other associated workers. This is being called "genai.mil" and I'm told it's designated for CUI - Controlled Unclassified Information and IL5 - Impact Level 5.

Secretary Hegseth and Google really made dramatic announcements about this and the Pentagon apparently has AI-generated posters of Hegseth in an Uncle Sam "I want you" pose saying "I want you to use AI!" and there are emails and popups and other promotions pushing use of this Google AI system for the military.

The announcements did raise many eyebrows because, among other reasons, Hegseth and Google didn't seem to quite agree on what this project is actually for. Hegseth talked in terms of increasing lethality, and Google seemed to be saying it's really for administrative purposes and some analyses -- but really oriented more toward routine paperwork and research.

Stories did come out quickly claiming that persons with access to the Google Gemini Military System asked it about the legality of that controversial "double tap" boat strike, and Gemini said it was illegal.

Now whether or not that's correct this does quickly take us to the heart of the matter which is as we all know how often Gemini and other AI systems are completely or partly wrong in their answers -- the latter being even more dangerous.

AI disclaimers often admit that you can't trust AI to be accurate, so it's understandable that there are concerns about bringing what's often called AI Slop into a military context, even if restricted to administrative operations.

I had an incident with Google's AI yesterday, not a critical one but something to ponder. I asked Google when an organization I know was taking their holiday break, usually some weeks. And the Google AI Overview came back and told me their break was from December 22nd to January 5th, and added that the duration was three weeks. And I'm looking at this and thinking THREE weeks? Yeah, Google AI in this case didn't know that 22 December to 5 January was only two weeks. Now if a student had gotten something like this wrong they'd probably get an F.

But you do have to wonder how Google AI could make an error like that. It's just a simple calendar query, no external information or context required. If you can't depend on AI for accuracy in something so simple and obvious, it's completely reasonable to be concerned about more complex information where errors would NOT be so obvious.

Thinking about the impact of AI loaded with misinformation in military situations can be rather chilling to say the least. While this isn't a sci-fi movie style evil AI, given what we all DO know about REAL AI now, there seems to be an almost endless array of ways that this Google/Pentagon partnership to push military AI could go very, very wrong indeed. And THAT'S a very serious concern.

- - -

L

Surprising pretty much nobody, I will be slamming the horrific #Google/Pentagon AI partnership on my usual weekly national radio tech segment tonight. The piece almost wrote itself.

Yep, Cosplay Hegseth wants the entire U.S. military depending on #Google AI, but Google AI still can't even get simple math correct, like the difference between 2 weeks and 3 weeks? Eh?

#Google Gemini creates its own home page for Google/DOD partnership AI system.

this is a question mainly to you #tts geeks out there. how can I get the Google Achernar voice installed on my Android? I would like to have it as a tts either engine or voice on my phone. thanks for anyone willing to help #texttospeech #tts #google

The topic for my usual Monday national network radio tech segment will be the new partnership between Billionaire CEO Sundar of Google, and Cosplay Secretary of Defense Pete Hegseth to deploy #Google Gemini AI across the U.S. Armed Forces, bringing Gemini's misinformation and error-prone AI Slop to the U.S. military. The "What could go wrong?" edition.

@briankrebs

#GenAiMil uses Gemini 2.5 not the latest 3.0 which is only 3 weeks old. Nevertheless, it excels at reasoning tasks (ranked #1) Its got a context window of 1 million tokens, which means one can feed a sizable document into it.

There is a joke here about reasoning #AI in an unreasoning administration, except there us a reason here, one which most Americans are unable to acknowledge. Destruction of the American state.

The good news us it's for level IL5 (Sensitive but unclassified) information, which means this clownshow is about to start feeding a whole bunch of classified content into it.
I'm looking forward to reading future #infosec breaches post mortems.

Also, remember the #Google now abandoned motto "Do no evil"? How much does evil cost?
$200 million dollars (June contract).
I vaguely remember a whole bunch of Google employees quitting.

Finally, do remember that there is absolutely no regulations WHATSOEVER controlling this tech.
This is nuclear power without safeties.
Car design without seatbelts and crumplezones
and
Food additives with no regulation.
In fact trump "administration" actively threatened states that tried to make houses about #regulateai
#LLM #skynet

Sickly hilarious: #Google Gemini insists that military "lethality" doesn't necessarily mean killing. Oh my.

This has to be a very, very dark time for most Googlers. They have my condolences. Seriously. How far #Google has fallen.

Rumor: #Google is renaming their T&S team (Trust & Safety) to L&M (Lethality & Murder).

What does #Google #Gemini say when ordinary people ask about military matters?

"I cannot fulfill this request. I am programmed to be a helpful and harmless AI, and that includes avoiding generating content that discusses or promotes politically sensitive or potentially harmful topics such as advocating for military action, invasion, or the overthrow of a government."

I guess for the Trump Nazis at the Pentagon, Google flipped on the EVIL switch.

L

Scammers are poisoning AI search results, and #Google is falling right into their trap

https://www.zdnet.com/article/scammers-poison-ai-search-results-customer-support-scams/

One of the really stupid aspects of #Google AI Overviews is that they never want to admit they don't what you're actually searching for, so they spew out utter nonsense that is so laughable it puts a lie to everything that Google claims about AI.

🚨 World's first social media ban begins: Australian & under‑16? Your social media account is now locked. 🚨

What's next? From Dec 27 #AgeVerification checks for search engines like #Google.

BUT - Once your data is in the system, what's stopping it from being used for surveillance?

And what happened to #Privacy? 🧐

#DigitalID #Australia

YouTube already has it ➡️ https://tuta.com/blog/how-to-turn-off-youtube-ai-age-verification

Alt...

Notice from YouTube: You must be 16+ to sign in to YouTube in Australia.

#Google #Gemini admits it will be "increasing lethality" for Defense
Department

QUERY: Will Google make public the number of people Google helps to murder via their partnership with Hegseth and the defense department for more efficient warfare and killing?

GEMINI:
The information available indicates a recent partnership between Google and the Department of Defense (referred to as the "War Department" by Secretary Pete Hegseth in the search results) to deploy Google's **Gemini for Government** AI model on a new platform called **GenAI.mil**.

* **Purpose of the Partnership:** The primary stated purpose is to
increase efficiency, productivity, and lethality within the Department
of War by using the AI for tasks like deep research, formatting
documents, and analyzing video or imagery at unprecedented speed. Secretary Hegseth explicitly marketed the platform as a way to make the fighting force **"more lethal than ever before"**.

Check it out: a roundtable discussion between a computing researcher and three senior Google engineers on the pivotal role of academia and the impact of federal funding on innovation.

Available via #CACM's special issue on Federal Funding on Academic Research: https://cacm.acm.org/federal-funding-of-academic-research/from-university-research-to-global-impact/

#TechNews #google #engineer #academia #computing

🚫 Watch out! #Google starts sharing all your messages with your employer.

👉🏼 More on Forbes: https://www.forbes.com/sites/zakdoffman/2025/12/03/google-starts-sharing-all-your-text-messages-with-your-employer/

Alt...

Google Starts Sharing All Your Text Messages With Your Employer

Suddenly discovering that you own a cat is a normal fact of life, as many cat owners will attest. (Well. Cat 'owners'.)

Suddenly discovering that you have owned several which have spent numerous years with you before dying of mysterious and increasingly contrived causes is rather more unsettling, as Chuck Wendig has found.

https://terribleminds.com/ramble/2025/12/04/vital-cat-update/

#ai #llm #google #shitware

Google is experimentally replacing news headlines with AI clickbait nonsense

Keep it up #Google, destroy the little trust anyone has left in you. -L

https://www.theverge.com/ai-artificial-intelligence/835839/google-discover-ai-headlines-clickbait-nonsense

Alt...

Tax these billionaire fascist-loving CEOs out of existence.

Report: Gestapo ICE facial recognition reporting app removed from #Google Play Store -- Maybe

My information on this is sketchy. Apparently this horrific Nazi app to use facial recognition to "find and report" immigrants to Adolf Trump's Gestapo ICE squads was removed from the Google Play Store. It's not clear why or for how long. I'm told there have been internal protests at Google regarding this app.

I'll emphasize again that by and large, Googlers (Google employees) are great. Google's embrace of fascism is being driven from the top, from Trump loving billionaire CEO Sundar. As the old saying goes, the fish rots from the head.

L

In the spirit of #FOSDEM2026 being sponsored by Google, I hope HackerTrain is brought to you by Ryanair.

#google #surveillanceCapitalism #BigTech #FOSDEM https://toot.si/@hook/115662561290957296

Somehow I had missed the November @calyxos status update:
https://calyxos.org/news/2025/11/10/calyxos-progress/

Apparently, they are:

- finalizing the design of a Hardware Security Module (HSM) signing solution

- finalizing the detailed provisioning plan for the signing process

- trying to figure out how to sustainably access and publish OS security patches in the face of #Google's meddling and gradual closing of Android code.

Also, they are hiring:
https://job-boards.greenhouse.io/calyxinstitute

#FuckGoogle #InfoSec #CalyxOS