-
35 votes
-
I am very privacy-oriented, but my recent Pixel phone somehow obtained all my pictures from my Linux computer
So I am attempting to swap phones, but because I am trying to use a pixel 9 xl and it was not previously on my network, I have to wait 40 days to unlock it so I can install GrapheneOS. I saw on...
So I am attempting to swap phones, but because I am trying to use a pixel 9 xl and it was not previously on my network, I have to wait 40 days to unlock it so I can install GrapheneOS.
I saw on Monday that suddenly there were a lot of photos dated from last Sunday on the phone's default "Photo" app. I have been keeping things to a minimum: I haven't logged into anything Google, and I've only installed F-Droid apps. Also, I had some issues with my desktop and did a clean reinstall 2 weeks ago.But still disturbingly, my ENTIRE ~/Picture directory (and subdirectories) from my PC were loaded onto my phone.
Now, I'd like to clarify, I do have a few Google accounts, but I have them logged into my desktop with containers on Firefox (particularly, I use one for a current hobby type situation that I have to use, and the other is a 20+ account that I've moved away from, but I still want to monitor).
I want to find out why anything from my PC ended up on this somewhat secluded phone. I have not attached it via USB, and while I have been attempting to limit my connections, I do need to access some of my rl/PC stuff on the phone. But I haven't logged into a google account on it, yet, all my photos showed up on it. I have not plugged it into the computer since I tried putting GrapheneOS on it, which failed due to it not being unlocked (PLEASE CORRECT ME IF I'M WRONG HERE, BECAUSE I STILL HAVE TO WAIT 2 WEEKS!), yet all these pictures that I would have never expected ended up on this phone.
And I just was looking around my ~/ directory, and I saw a directory titled .nuget... I checked pacman (I'm on Arch, so that's my package manager), and it's not installed, but I deleted it because it had a lot of sketch files that ... okay, so I deleted the directory and honestly I don't have it anymore to state what exactly was in it. But I'm really tired and it triggered issues, and I looked and I see that nuget is not installed... so okay, I'm just gonna end this here because I do need to go to bed.
But, would anyone be able to provide any assistance/advice/suggestions on how the heck my phone magically obtained my Linux desktop Picture files?
23 votes -
The missing 11th of the month
32 votes -
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
22 votes -
How I analyzed 1,378 restaurants using Places API to find hotspots in my city
14 votes -
"A calculator app? Anyone could make that."
54 votes -
Building a personal, private AI computer on a budget
24 votes -
Booting Linux off of Google Drive
23 votes -
Simple ways to find exposed sensitive information
9 votes -
Secrets from the algorithm: Google Search’s internal engineering documentation has leaked
30 votes -
What useful tasks are possible with an LLM with only 3B parameters?
Playing with Llama 7B and 13B, I found that the 13B model was capable of doing a simple task, rewriting titles in sentence case for Tildes submissions. The 7B model doesn't appear capable of the...
Playing with Llama 7B and 13B, I found that the 13B model was capable of doing a simple task, rewriting titles in sentence case for Tildes submissions. The 7B model doesn't appear capable of the same task, out of the box.
I heard about Android's new AICore available on a couple of new devices. But it sounds like Gemini Nano, which runs on-device, can only handle 2B or 3B parameters.
Is this size of model useful for real tasks? Does it only become useful after training on a specific domain? I'm a novice and wanting to learn a little bit about it. On-device AI is an appealing concept to me.
12 votes -
Please proofread this AI-generated AutoHotkey script
For my job I need to copy a person's name out of a field and split it into first and last names. I have a AHK script that can do this but my version only works with simple, one-word,...
For my job I need to copy a person's name out of a field and split it into first and last names. I have a AHK script that can do this but my version only works with simple, one-word, non-hyphenated names. I tried prompting Gemini as below.
There is a line of text consisting of one or more words, a comma, then one or more words. write an autohotkey 1.1 script to select everything before the comma, store it to a variable called firstname, then select everything after the comma and store it to a variable called lastname. thanks
(the firstname and lastname variables should be swapped as the last name would come before the comma, that was my error)
Here's the AutoHotkey 1.1 script to achieve what you described:
; This script splits a text line into first and last name based on a comma #NoEnv ; Recommended for performance and compatibility. SendMode Input ; Simulates keystrokes for reliable input. ; Function to split the text Func SplitText(_text, firstName, lastName) { StringSplit, parts, _text, `,` if (parts[1]) { firstName := parts[1] ; Assign first name lastName := SubStr(_text, 1 + StrLen(parts[1])+1) ; Extract last name after comma (including space) } else { firstName := _text ; Handle cases without a comma lastName := "" } } ; Hotkey to trigger the script (replace F2 with your desired key) F2:: Send, ^c ; Copy the selected text to clipboard clipText := ClipboardAll ; Read the clipboard content SplitText(clipText, firstName, lastName) ; Call the function to split the text MsgBox, First Name: %firstName%`nLast Name: %lastName% ; Optional: Clear clipboard to avoid unintended pasting (comment out if not desired) ; Clipboard := Return
Explanation:
#NoEnv and SendMode Input: These lines are included for performance and reliable input simulation.
Func SplitText(_text, firstName, lastName): This function takes the text (_text) as input and assigns the split parts to variables firstName and lastName.
StringSplit, parts, _text, ,:** Splits the text based on the comma (,`) delimiter.
if (parts[1]):** Checks if there's a second part (i.e., text after the comma).
If true, the first part is assigned to firstName and the text after the comma (including the space) is extracted using SubStr and assigned to lastName.
else:** If there's no comma, the entire text is assigned to firstName and lastName is set to an empty string.
F2::: This line defines a hotkey. When F2 is pressed, the following actions occur:
Send, ^c:** Copies the selected text to the clipboard.
clipText := ClipboardAll:** Reads the copied text from the clipboard and stores it in the variable clipText.
SplitText(clipText, firstName, lastName):** Calls the function to split the copied text into first and last names.
MsgBox:** Displays a message box showing the extracted first name and last name.
Optional: Clear Clipboard: The commented line Clipboard := clears the clipboard content after processing. Uncomment this line if you want to avoid accidentally pasting the copied text elsewhere.Edit: To answer questions, and provide info I probably should have from the beginning: I'm a medical transcriptionist using AHK with my job's software (Emdat Inscribe) and a word expander (Instant Text). Inscribe seems to be browser-based but functions as a standalone app. I already have dozens of AHK 1.1 macros; my .ahk file has over 2000 lines, although I'm sure it's terribly written code. This is also why I'm disinclined to switch to AHK 2.0 since I have no desire to rewrite everything unless absolutely necessary. The first part of this macro is a bunch of keypresses to jump to the relevant patient info field, then this part would be used to store the names appropriately. I already have hotkeys to use the variables as needed and most macros are limited with #ifwinactive to Inscribe.
6 votes -
Google's Say What You See - Come up with a prompt to match an already generated image
12 votes -
Critical 0day in WebP: Google assigns a CVE for libwebp and gives it a 10.0 base score.
28 votes -
Typograms — an image format for lightweight diagrams
18 votes -
Web Environment Integrity - A Google proposal for general web drm
47 votes -
Understanding DeepMind’s sorting algorithm
5 votes -
SourceHut will blocklist the Go module mirror
13 votes -
Google introduces Carbon, an experimental replacement for C++
11 votes -
Is LaMDA Sentient? - An Interview
5 votes -
Chrome OS Flex announced
4 votes -
Why does a completely local, self-contained html file need to access gstatic.com?
So, I'm a privacy advocate (or paranoiac, depending on your perspective). I run both uMatrix and NoScript plug-ins (among others) in my Firefox browser, so I can see when and where websites send...
So, I'm a privacy advocate (or paranoiac, depending on your perspective). I run both uMatrix and NoScript plug-ins (among others) in my Firefox browser, so I can see when and where websites send calls out to other locations, and block the ones I want ... google analytics, google fonts, google-apis, google tag manager, and gstatic are all ubiquitous out there, probably 99% of websites use at least one of them (PS: Tildes is in the 1%; yeay, Deimos).
And note ... there may well be nothing at all wrong with any of those sites/services ... but Google has a global all-encompassing Terms and Conditions policy that says, you use anything of Theirs, and They are allowed to harvest your personal data and make money off of it.
And I do not accept those terms.
Okay, that's the prologue. The deal is, I have a small piece of documentation, just basic "how to use this" info, for a WordPress plug-in. It is in .html format, with bundled bootstrap and jquery and a few other assets.
Nothing, anywhere in the entire folder, references gstatic. And yet when I open this local, on-my-computer-only html file ... my browser tells me that it is trying to connect to gstatic.com.
Anyone happen to know why/how that is happening?
4 votes -
Google Docs will now use canvas based rendering
13 votes -
Misinformation about Permissions Policy and FLoC
8 votes -
Version 2 of Google’s Flutter toolkit adds support for desktop and web apps
7 votes -
Help with Google accounts authentication on iOS/iPadOS
Edit: This was resolved by @tomf (cf. this comment). Google’s account authentication appears to broken for me for some reason. I have several devices and several Google accounts accumulated over...
Edit:
This was resolved by @tomf (cf. this comment).
Google’s account authentication appears to broken for me for some reason.
I have several devices and several Google accounts accumulated over the years.
Accounts:
- Work Google account (this was set up by IT staff at the company where I work as they are a paying enterprise Google services customer)
- Undergraduate University account (this was set up when I attended undergrad, where the University is a paying Google services customer)
- Graduate University account (this was set up when I attended for grad school, where the University is a paying Google services customer)
- Personal Google account (this was set up a long time ago, it’s just a non-paid, consumer Google account)
Under iOS and iPad OS, Google apparently asks you to download the official Google app in order to sign in and “trust” devices, so that they can send you prompts to acknowledge when you sign in on other devices. There is also the Google Authenticator app that lets you do traditional 2FA.
Further background, I got an iPhone 12 Pro circa October 2020. I gave my old iPhone handset to my dad (after signing out of everything and resetting it according to Apple’s instructions). Ever since, I’ve been having issues with logging into my Google accounts from the new iPhone, my iPad, and my Mac (provided by work). I’m actually afraid to log out of my work Google account on my work Mac, because I’m afraid I won’t be able to log in again, and that would prevent me from being able to get work done.
For example, let me walk through the steps I would normally take to log in to my Undergraduate University Google account on my iPad:
- Open the Google app
- Tap user icon in top right corner
- From the modal menu, tap the downward chevron (circled in red)
- Tap “Add another account” (circled in red)
- Tap “Continue” on the confirmation widget when prompted
- Enter the Gmail address for the account in the provided “Email or phone” input box and tap “Next”
- At this point, I wait for the progress indicator (the blue bar with the red arrow pointing to it) to indefinitely traverse from left to right over and over again and I cannot progress further.
Virtually the same steps can be reproduced from my iPhone by going to accounts.google.com from any browser (I’ve tried Safari and Chrome).
The same sort of authentication redirect from accounts.google.com happens when trying to add my associated Gmail accounts to my iOS devices from the Settings > Mail > Accounts > Add Account, and similarly stalls at the same point.
I’ve tried logging out of my accounts from my personal Mac where I can still log in from google.com, and also tried going into the security settings for the accounts and disabling, then re-enabling 2FA (I can receive the text message with the code to associate my iPhone as a second factor authenticator, so Google knows my phone number).
Google’s support documents don’t provide any guidance on this situation where the accounts.google.com authentication hangs, and there seems to be no way to contact a human being at Google to provide technical support. I’ve searched their help portal/forums, and found nothing similar to my issue. They point me down a tree that ends here, which is not useful to me.
If Google’s services don’t work for you, it seems to be your problem, not theirs. I get that I’m not paying for their services, so it is totally unreasonable for me to expect any sort of technical support from Google. But, at the same time, it seems very strange that I am alone in my use case of simply trying to log into my accounts that have worked for years in the past without issue.
Anyone have advice on next steps?
5 votes -
Google LLC v. Oracle America, Inc. lawsuit: Can APIs be copyrighted?
14 votes -
Google using Core Web Vitals in their search rankings will be a positive change, but developers should be careful not to fixate solely on those three metrics
6 votes -
Google should rotate their email DKIM keys periodically and publish past secret keys, in order to remove the unintended capability for authenticating years-old emails
16 votes -
Dear Google Cloud: your deprecation policy is killing you
12 votes -
Historical programming-language Usenet groups disappearing from Google Groups, including comp.lang.lisp
6 votes -
Finding a problem at the bottom of the Google stack
7 votes -
An update on bradfitz: Leaving Google
7 votes -
Intent to Deprecate and Freeze: The User-Agent string
18 votes -
Changing your name is a hard unsolved problem in Computer Science
14 votes -
Google Chrome: Behind the Open Source Browser Project (2008)
6 votes -
Exploring Google Stadia's "Negative Latency"
26 votes -
Chrome 0-day exploit CVE-2019-13720 used a race condition and a Use-After-Free to install persistent malware on Windows
10 votes -
DeepMind's StarCraft II AI "AlphaStar" has reached the top-level Grandmaster league using multi-agent reinforcement learning
13 votes -
Google Claims ‘Quantum Supremacy,’ Marking a Major Milestone in Computing
33 votes -
Bigger Rewards for Security Bugs
6 votes -
How To Build An App: Everything You Didn't Know You Needed To Know | Tom Scott
8 votes -
Google open-sources their robots.txt parser and releases an RFC for formalizing the Robots Exclusion Protocol specification
10 votes -
Go is Google's language, not ours
15 votes -
Apple arms web browser privacy torpedo, points it directly at Google's advertising model
4 votes -
XSS attacks on Googlebot allow search index manipulation
7 votes -
Algorithms Allowed: a project that tracks usage of Google and Facebook assets in countries under US sanctions
6 votes -
An All-Neural On-Device Speech Recognizer
7 votes -
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
15 votes -
Does the Oracle v. Google court case mean that Wine/DXVK is illegal?
I've been thinking about this but based on the current rulings in the Oracle v. Google court case, it would seem that APIs are indeed copyrightable. This would mean that Wine would be infringing...
I've been thinking about this but based on the current rulings in the Oracle v. Google court case, it would seem that APIs are indeed copyrightable.
This would mean that Wine would be infringing on Microsoft's copyright of the Windows API and system calls. Of course it wouldn't matter until Microsoft actually does something about it. But as Wine gets better and better and its market share higher and higher, I worry that Microsoft might set their sights on Wine now that they have the law on their side.
15 votes