Microsoft’s aggressive AI push in Windows 11 through 2025 brought upon themselves the title Microslop. Unfortunately for the company, it’s everywhere on social media, and there isn’t a way to stop the spread, unless, of course, it’s their own Discord server.

Windows Latest was first to notice that the word “Microslop” was actively filtered in the official Microsoft Copilot Discord server. Any message containing the term is automatically blocked, and users see a moderation notice stating that the message includes a phrase considered inappropriate by server rules.

However, things fell apart when users noticed the filter and began testing it with variations of the word Microslop, along with other unflattering words, eventually forcing the moderators to lock the server, leaving all users in the dust, and not just the offenders.

Copilot Community channel doesn’t allow messages to be shown, including the history

Microsoft blocks “Microslop” in official Copilot Discord, users quickly find workarounds

The extreme backlash that Microsoft has to endure every day on social media is nothing short of extraordinary. Surely the company is responsible for this fallout, as they prioritized AI more than the stability of the OS that it needs to run on.

User frustration quickly spilled into comment sections, memes, and community spaces tied to Microsoft’s AI push. Copilot, being the most visible face of that effort, has naturally become the scapegoat. So when a nickname like “Microslop” starts trending across socials, it was only a matter of time before it reached official channels as well.

Windows Latest found that sending a message with the word “Microslop” inside the official Copilot Discord server immediately triggers an automated moderation response. The message does not appear publicly in the channel, and instead, only the sender sees the notice stating that the content is blocked by the server because it contains a phrase deemed inappropriate.

From what we can tell, this is a server-side keyword filter. It is not unusual for brand-run Discord servers, especially those meant for product feedback, support, and feature discussions. Such servers are not fans of meme-driven commentary, especially if it deprecates the brand.

Of course, the internet rarely leaves things there. Shortly after Windows Latest posted about Copilot Discord server blocking Microslop on X, users began experimenting in the server with variations such as “Microsl0p” using a zero instead of the letter “o.”

Predictably, those versions slipped past the filter. Keyword moderation has always been something of a cat-and-mouse game, and this isn’t any different.

To be fair, it’s not rare for companies to moderate brand-specific insults or viral memes within their official communities to maintain a certain tone. The Copilot Discord is a space for announcements, user stories, and support discussions. From that perspective, blocking a derogatory nickname is understandable.

Microsoft locks Copilot Discord server after moderation backlash escalates

What started as a simple keyword filter quickly snowballed into users deliberately testing the restriction and posting variations of the blocked term.

Accounts that included “Microslop” in their messages first got banned from messaging again. Not long after, access to parts of the server was restricted, with message history hidden and posting permissions disabled for many users.

At the time of writing, several channels display limited visibility or locked states, indicating the server was effectively put into containment mode as moderators tried to regain control of the conversation.

This kind of lockdown is fine as long as the moderators’ goal is to pause activity and prevent further escalation before normal discussions resume. But at this point, we’re not sure if the server will continue to function as it used to.

Microsoft’s brand image might already be at an all-time low, and even as the company announced plans to fix Windows 11 with performance improvements and less AI, the software giant can’t risk getting more hatred towards their expensive investment in Copilot, especially since Microsoft’s head start in AI is starting to be overshadowed by competitors like Anthropic, Google, OpenAI, and maybe even Apple in the near future.

The Copilot community was far more positive when this Discord server first launched

Back in December 2024, when Microsoft invited users to join the Copilot Discord server through an official X post, the response was largely curious and enthusiastic, with people willing to explore the AI’s capabilities.

Since then, sentiment around Copilot and its usage has dropped alongside Microsoft’s broader AI push across Windows 11. The company’s aggressive rollout and constant branding drew criticism from most users because Windows 11 had more issues to deal with than ever before.

At its present state, Copilot has added some capabilities that are genuinely useful in day-to-day workflows. Features like connectors can pull contextual data from services such as Google Contacts, Gmail, and Outlook to retrieve phone numbers or email addresses directly inside Copilot, something competing tools like Gemini have not yet cracked, as we found in our detailed testing.

It remains to be seen if this episode fades as a minor community moderation story or becomes another chapter in Microsoft’s complicated relationship with its AI rollout. For now, it highlights the tension between a company pushing hard toward an AI-first future and a user base that is still deciding how much of that future it actually wants.

The post Microsoft gets tired of “Microslop,” bans the word on its Discord, then locks the server after backlash appeared first on Windows Latest

Windows 11 has a new policy called “Make Print Screen key yiedable,” which allows third-party apps to intercept the keyboard shortcut. This means third-party apps can easily use the ‘Print’ screenshot, which typically opens Snipping Tool or Windows 11’s built-in screen capture interface.

There are many ways to capture a screenshot in Windows 11, but the most popular shortcut remains the Print key. That’s given because the key itself is called “Prntscr,” which stands for Print Screen. On most PCs, when you press the Print key, it opens the Snipping Tool.

As noticed by Tero and verified by Windows Latest, Microsoft is testing a new Group Policy, which enables third-party apps to override the default screenshot key.

In Build 26300, if you open Group Policy Editor, which requires Windows 11 Pro, and go to Computer Configuration > Administrative Templates > Windows Components > File Explorer, you’ll find a policy called “Make Print Screen key yieldable.”

By default, this policy is set to “not configured,” which means third-party apps can use your Print key whenever they want, replacing ‘Snipping Tool’ as the default app.

“This policy setting determines whether the Print Screen key can be yielded to other applications,” Microsoft noted in an explanation seen by Windows Latest.

“If you enable this policy setting, the Print Screen key can be intercepted by applications, allowing them to override the default screenshot functionality. If you disable this policy setting, the Print Screen key will retain its legacy behavior for taking screenshots and cannot be intercepted by applications.”

If you don’t want third-party apps to take over the Print key, you should set the policy to “Disabled”. In all other cases, you should leave it as it is. Third-party apps randomly do not hijack your Print key, and if they do, you can always remove the app or simply use the Group Policy.

In our tests, Windows Latest observed that the Group Policy that gives you greater control over the Print key requires a reboot to fully apply the changes.

It’s not the first time Microsoft has tried to change how the Print Screen key works

Back in 2023, Windows Latest spotted a new toggle “Use the print screen key to open Snipping Tool” under Settings > Accessibility > Keyboard that lets you block Print Screen from opening Snipping Tool by default.

Microsoft even called it out in a 2023 blog post: “Pressing the print screen key will now open Snipping Tool by default. This setting can be turned off via Settings > Accessibility > Keyboard. If you have previously modified this setting yourself, your preference will be preserved.”

That toggle showed up in preview builds at the time, but it’s effectively gone now. On Windows 11 24H2 (and 25H2), heading to Settings > Accessibility > Keyboard doesn’t show any option to control Print Screen behaviour when Snipping Tool is installed.

What makes it more confusing is that Snipping Tool still points you to Accessibility settings to change the Print Screen shortcut, but the setting it references isn’t there anymore.

So you get sent to the “right” place, only to hit a dead end. Either way, the new Group Policy is more powerful for managing the Print Screen key, and it’s now rolling out to users.

The post Microsoft finally gives you greater control over Print screen key in Windows 11, including access to third-party apps appeared first on Windows Latest

Engadget reports: In a lengthy post on Truth Social on February 27, President Trump ordered all federal agencies to "immediately cease all use of Anthropic's technology" following strong disagreements between the Department of Defense and the AI company. A few hours later, the U.S. conducted a major air attack on Iran with the help of Anthropic's AI tools, according to a report from The Wall Street Journal. Even Trump's post noted there would be a six-month phase-out for Anthropic's technology (adding that Anthropic "better get their act together, and be helpful during this phase out period, or I will use the Full Power of the Presidency to make them comply, with major civil and criminal consequences to follow.") Anthropic's Claude technology was also used by the U.S. military less than two months ago in its operation in Venezuela — reportedly making them the first AI developer known to be used in a classified U.S. War Department operation. The Wall Street Journal reported Anthropic's technology found its way into the mission through Anthropic's contract with Palintir.

Read more of this story at Slashdot.

If you've been exploring local AI with Microsoft Foundry Local, you've learned that running a chatbot frontend on Windows Server or Windows Client that you can access over the network comes with a challenging set of dependencies.

FoundryLocalWebUI is a simple, self-contained web frontend for Foundry Local that runs on IIS, works on both Windows Server and Windows Client, and uses common Windows ecosystem components.

You can find the project on GitHub: https://github.com/itopstalk/FoundryWebUI

Here is an explanatory video here: https://youtu.be/IGWNhSQziZI

FoundryLocalWebUI is a lightweight web application designed to be hosted on IIS, which is already available to Windows Server and can be enabled on Windows Client with a few clicks. There is no need to install a separate web server, worry about a package manager, or spin up a Windows Subsystem for Linux environment.

FoundryLocalWebUI is an experimental proof of concept. It doesn't support multiple users and just provides basic chatbot functionality. It's suitable if:

• You're evaluating Foundry Local and want a quick, no-fuss frontend to test models through a browser rather than the command line.
• You want to keep your deployment footprint small and your dependencies minimal.
• You're running Windows Client and want a local chat interface without the overhead of heavier solutions.

The setup process is intentionally straightforward. 

Make sure that Git is installed:

winget install --id Git.Git -e --accept-source-agreements --accept-package-agreements

Clone the repo and run the installer (you'll have to use set-executionpolicy to allow the PowerShell script to run)

cd C:\Projects 
git clone https://github.com/itopstalk/FoundryWebUI.git FoundryLocalWebUI 
cd FoundryLocalWebUI 

# Windows Server 2025: 
.\Install-FoundryWebUI.ps1 

# Windows 10/11: 
.\Install-FoundryWebUI-Desktop.ps1

Full setup details are in the GitHub repo, and the walkthrough video covers the process end to end if you'd rather follow along visually.

This is still early days for the project, and I'd love to hear from the community. Local AI is becoming a real option for organizations that need to keep data on-premises and maintain control over their infrastructure. 

Spin up a WS 2025 eval edition VM and give it a go.

There’s been quite a bit of hype around the use of AI for vibe coding applications. Add in the use of a Ralph loop and we’re getting close to being able to automatically generate entire applications. But how much of this is hype and how much is reality. In this post I’ll walk through using a simple Ralph loop with the latest Uno Platform AI tooling to build an application from just a simple specification. I let it run overnight whilst I slept, so we’ll see what it produced and where we should go next.

So, here’s a quick overview of my setup:

• Running on Windows with VSCode
• Using a devcontainer setup under WSL to make sure Claude can’t go rogue on my PC
• I created the initial Uno Platform application using “dotnet new unoapp -preset recommended” to create my application using the latest Uno Platform guidance (Material, MVUX, Navigation etc)
• I’m using Claude Code
• I’ve added both Uno Platform MCP servers
• Validated that both Uno Platform MCPs are connected and have tools loaded

IMPORTANT: In order to get a good outcome it’s very important that the Uno Platform App MCP is connected and is reporting tools (there should be 11 at the time of writing). If the tools don’t load after 30 seconds (default timeout), it’s likely to be a result of one or two reasons:

• Not Authenticated with Uno Platform account. If you’re in a container/WSL you can launch the Studio app by running (substitute {version} with the version that you have. If none, run dotnet restore on your Uno Platform app):
  dotnet ~/.nuget/packages/uno.settings.devserver/{version}/tools/manager/Uno.Settings.dll
• Not able to resolve Solution or Project that references Uno Platform. Change to the directory that has the Solution (.sln) file before running Claude.

Whilst I’m using Claude in this example, the above setup, including the instructions for validating MCPs, applies to other AI agent CLIs (eg Codex).

Application Specification

Before I got started building the application I launched an interactive session with Claude and in Plan mode proceeded to describe the set of features for my application. I started with a brief description of the app:

“Help me determine the specifications for a financial tracking and planning application”

Through structured Q&A, , the following was established:

• Audience: Personal/household use
• Platforms: Web (WASM), Desktop (Win/Mac/Linux), Mobile (iOS/Android)
• Tech stack: Uno Platform (.NET/C#), SQLite, MVUX, Uno Material, LiveCharts2
• Data entry: Manual only (no bank sync/import)
• Storage: Local only (no cloud)
• Auth: Local account — username + BCrypt password + recovery phrase + optional PIN

8 features were defined (F1–F8):

#	Feature
F1	Account Management — multiple account types, offset accounts, reconciliation
F2	Transaction Tracking — Manual vs Planned, recurring rules, interest charge computation
F3	Planning (Scenario Modelling) — branching scenarios, projection engine, comparison view (replaced the original “Budgeting” feature at your request)
F4	Net Worth Tracking — share holdings, properties, loan-secured property equity/LTV
F5	Financial Goal Planning — savings targets, debt payoff, on-track status
F6	Reporting & Visualization — 5 chart types, CSV export
F7	Authentication & Security — registration, login, optional PIN, forgot-password flow
F8	Settings & Data Management — categories, recurring rules, localisation, data export

All 8 features were broken down into 42 issues on GitHub with full acceptance criteria and linked to their parent epics.

Basic Ralph

Sometimes when I hear Ralph discussed it ends up being overly complex, for example requiring the use of plugins. This is one of those topics that you can make as complex as you want. For me, it’s just a basic execution loop that works through a predefined list of tasks until completed.

With this in mind, the first thing to do was to create an ordered list of my GitHub issues for my Ralph loop to work through. Again, I used Claude for this with the following prompt:

Retrieve all open github issues. Sort them in the order that they should be completed (ignore epics) and write them to a file openissues.md

This created an openissues.md file with issues listed as follows:

Now onto the Ralph loop itself. This is just a bash script (Credit to Dan Vega in his video The Ralph Loop Explained: Automate AI Coding Tasks in Java where I borrowed the structure of this script from).

#!/bin/bash

SLEEP_BETWEEN=10
LOG_DIR="logs"

mkdir -p "$LOG_DIR"

for ((i=1; i<=$1; i++)); do
  echo ""
  echo "****************************************"
  echo "Iteration $i of $1"
  echo "****************************************"

  outfile="$LOG_DIR/iteration_${i}.log"

  claude --dangerously-skip-permissions -p "@openissues.md @progress.txt \
0. Make sure uno and unoapp MCP are connected and that unoapp MCP has 11 tools available. After 30s if the unoapp MCP tools are not available, do not update GitHub issue and exit immediately. \
1. Read progress.txt to see what has been completed. \
2. Get the next issue from openissues.md. \
3. If there are no issues, output <promise>COMPLETE</promise> and exit. \
4. Complete the issue as required. \
5. If the issue requires code changes, make the necessary changes and commit them to GitHub. \
6. Ensure there are adequates tests for the changes you made. \
7. If the issue requires documentation changes, update the relevant documentation. \
8. Run the application and verify that the issue is resolved. Capture screenshots or logs as evidence of the fix. \
9. Update the GitHub issue with a comment describing how you resolved the issue, including any screenshots or logs. Close the GitHub issue as done. \
10. Append your progress to progress.txt with what you completed. \
11. If ALL tasks in openissues.md are complete, output <promise>COMPLETE</promise>. \
ONLY WORK ON ONE TASK PER ITERATION." > "$outfile" 2>&1 || {
    echo "Warning: Iteration $i failed (exit code $?). See $outfile for details. Continuing..."
    continue
  }

  cat "$outfile"

  if grep -q '<promise>COMPLETE</promise>' "$outfile"; then
    echo ""
    echo "openissues.md complete after $i iterations!"
    exit 0
  fi

  if (( i < $1 )); then
    sleep "$SLEEP_BETWEEN"
  fi
done

echo ""
echo "Reached $1 iterations. openissues.md may not be complete."

To execute you can just call

bash ralph.sh 100

This will run the loop 100 times, which in my case was enough to complete all 42, non-epic, GitHub issues.

And now you wait….. and wait…. and once you’ve verified that the first iteration doesn’t blow up and something is happening (you should see files being created and logs written)…. you can leave Ralph to it and come back in a few hours. I actually just went to bed and checked on the progress when I work up.

Ralph is Not a Designer

Actually, this should be Claude isn’t a designer, or at least is no substitute for a good UX designer. After working all night my Ralph loop and Claude had concocted what I’m sure is a fully functional app that meets my specifications. In fact, the over 1200 tests it created hopefully verifies that at least the functionality works. However, as the following screenshot of the MainPage will attest to, there was no thought towards building a usable interface.

There’s no doubt that Claude, Codex etc are all super powerful tools but if you don’t provide them with enough input, you’re at their mercy. In this case I’d come up with a detailed specification but hadn’t spent time working out what the UX should be. I ended up with a basic, input based, UX where there were CRUD style interfaces for each of the elements of the data model.

Summary

There are two clear takeaways from this. Firstly, building apps, even cross platform apps, has been dramatically condensed – we’re talking weeks, perhaps even months, of development down to a mere few hours. Secondly, that more time spent coming up with specifications, application flow, designs, will significantly improve the quality of the outcome.

From here I clearly need to spend more time with Claude coming up with a better UX for the application. In the past, this would have required reworking the application to adapt it to the new UX. However, since it only took a few hours to build the first version, and I don’t need to worry or care about users having to upgrade to a new version, why not completely rebuild the application from scratch!!! I’ll leave you with this thought – whether it’s better to adapt or rebuild, now that development cost isn’t what it used to be.

The post Ralph built a Cross-Platform app using Uno Platform whilst I slept. appeared first on Nick's .NET Travels.