Posted on

10x Faster IT Troubleshooting: How I Used AI to Solve a Mysterious Windows Process Loop

It’s one of those problems that every IT pro, sysadmin, or power user dreads. Not a blue screen, not a server-down emergency, but a small, persistent, and maddening “ghost in the machine.”

For me, it was a flashing cursor.

For about five minutes every few hours, my mouse cursor in Windows 11 would flash the “waiting” or “processing” icon. Every. Single. Second.

As a problem, it was just annoying. But as a puzzle, it was infuriating. My system was fully up-to-date, drivers were current (or how I liked them), and resources were normal. Task Manager showed… nothing. No CPU spikes, no disk thrashing, no memory leaks.

I work in IT. These sort of things shouldn’t happen to me!
Who is going to help me!?? I am THE HELPDESK!!
(or at least passed by that title to get to my current position.)

cannotdisplay.com flashing mouse cursor every few seconds issue. solved. AI companion helps to fix this annoying flashing mouse waiting timer that wont stop!
cannotdisplay.com flashing mouse cursor every few seconds issue. solved. AI companion helps to fix this annoying flashing mouse waiting timer that wont stop!
cannotdisplay.com flashing mouse cursor every few seconds issue. solved. AI companion helps to fix this annoying flashing mouse waiting timer that wont stop!

Why, oh why is this happening to me!
This is a user problem, not something that I should have to diagnose and solve on …my own device…?

I could have spent the next four hours solving it the old-fashioned way. Instead, I did it in under 30 minutes by using an AI as my troubleshooting co-pilot. This is the story of how that collaboration worked, and why it’s a game-changer for IT pros – at least in some situations.

The Problem: A Ghost in the Machine

My first instinct was to use the process of elimination. The “human” part of the troubleshooting.

  • Was it my screenshot tool, picpick.exe? I killed the process. Nope.
  • Was it a stuck powershell or wt.exe script? Killed those too. No change.
  • Was it a browser tab? Or browser process? Or Windows App?
    Restarted Brave.
    Restarted that long running google updater/chrome process,
    Restarted EdgeWebView2 (which all modern Windows Apps use). Still flashing.
  • Was it the classic: explorer.exe? Restarted it. Nothing.

I was 15 minutes in, and all I had done was prove what wasn’t the problem. Not necessarily a bad thing.

My next step was to break out the heavy-duty logging tools, dig through a million lines of text, and resign myself to a long, tedious hunt.
This is the “grunt work” of IT – the part of the job I can do, but don’t exactly enjoy.

The “AI Nudge”: Asking for a Second Pair of Eyes

Instead of diving into that digital haystack of logs, I took a different approach. I opened an AI assistant.

I didn’t ask it to “fix my PC.” That’s not how this works. I treated it like a junior sysadmin or a “second pair of eyes.” I explained the symptoms and what I had already tried.

My prompt was something like:

"I've got an intermittent flashing 'waiting' cursor on Windows 11. It's not a high-CPU process; Task Manager is clean. I've already restarted explorer and other common apps. I suspect it's a process starting and stopping too fast to see. What's the best way to catch it, which logs should we look at first, or which tools should we spin up?"

The AI’s response was the “force multiplier.”

It didn’t give me a magic answer. It gave me a precise, actionable workflow. It validated my theory (a fast process loop) and recommended the perfect tool and the exact filter to find it. It basically said, “You’re right. Now, go here, use this tool, and apply this specific filter to see only newly created processes.”

This is the power of human-AI collaboration. The AI didn’t replace my skill; it augmented it. It saved me 30 minutes of searching through old notes, Googling, and trying to remember the exact syntax for a tool I use maybe six times a year.

Collaboration: From Digital Haystack to Prime Suspect

With the AI’s “nudge,” I had my prime suspect in less than 60 seconds.

I ran the tool with the filter, and what was previously an overwhelming flood of data became a crystal-clear, one-line-per-second log of the exact same process being created and destroyed.

I’m writing a full, technical step-by-step tutorial on this exact method (at some point!), but the short version is: the filter worked perfectly.

The process name immediately told me it was a system component related to network connections. This is where I, the human, took back control.

  • AI Clue: It’s a network process.
  • Human Hunch: If the client is spamming a network request, the server must be rejecting it.

I immediately logged into my network-attached storage (NAS) / file server and opened the access logs.

Bingo.

A wall of red: “Failed to log in.” My PC’s IP address, every single second, trying and failing to authenticate.

The “Aha!” Moment and the 5-Minute Fix

I now had two pieces of the puzzle: a network process on my PC failing in a loop, and a file server rejecting its login – however, upon testing I could still access the file share? Nothing seemed to be blocked? It is all working as expected! (other than my BLINKING CUIRSOR!)

I could have figured it out from here, but I turned back to my AI co-pilot for the “why.” I fed it the two new clues:

 "I've got this process spamming, and my server is blocking it but I still have access? What is going on here and what process could be causing this if everything works as it should?"

My AI buddy instantly provided the obscure, “textbook” knowledge. It explained a specific, built-in Windows fallback behaviour. When a primary connection to a network share (via the normal SMB protocol) fails, Windows will sometimes try to “help” by falling back to a different protocol (WebDAV), creating this exact kind of rapid-fire loop.

The root cause was that I had updated my file server’s software a few days ago, and my PC was still trying to use an old, expired, cached credential – part of it updated, the other (seldom used) web browser access fall-back element – had not caught up. And according to my AI, once started the process was ‘handed off‘ to the ‘system’ to complete, thus is not tied to a browser and is why a browser restart or closure had not cleared the issue.

The fix was laughably simple.

  1. I went to Windows Credential Manager.
  2. I found the saved credential for my file server.
  3. I clicked Remove.
  4. I browsed to the server again and re-typed my password.

The flashing stopped. Instantly. The problem was solved.

AI Isn’t My Replacement, It’s My Co-Pilot

What would have been a long, annoying afternoon of troubleshooting was over before my coffee got cold.

AI didn’t solve the problem. I solved the problem.

But AI acted as the perfect co-pilot. It streamlined the most tedious parts of the process, provided the “second opinion” to keep me on track, and supplied the deep, “encyclopedic” knowledge when I needed it.
It let me skip the grunt work and focus on the smart work – the analysis, the hunch, and the fix.

This is the future of IT. It’s not about being replaced by AI;
it’s about being 10x more effective by using it.

If you’re curious about the specific tools and filters I used to catch that rogue process, keep an eye out for my next post: “[SOLVED] Beyond Task Manager: Simple Guide to Finding Process Loops with Process Explorer and Procmon.” – when I eventually post it!

Posted on

[SOLVED] UniFi AP Firmware 6.7.31: Breaking Wireless Meshing and Causing Channel Hopping – Here’s the Fix.

Unifi Firmware 6.7.31 Mesh Problem and Fix

A recent official firmware update for several popular UniFi Access Points, version 6.7.31 (Released: Tuesday, September 23rd, 2025), is causing significant network instability for some users, particularly those who rely on wireless meshing or custom channel configurations. While the official release notes claim “Improved overall AP stability,” user reports indicate the opposite can be true.

This release is only for these models:

  • U6-LR/U6-Lite/U6+
  • UAP-nanoHD/FlexHD/BeaconHD/IW-HD
The Quick Fix TLDR:

UniFi firmware 6.7.31 is causing mesh instability due to a channel hopping bug. To fix this, manually downgrade the affected Access Point to a stable version like 6.7.17 via the UniFi Controller’s Manual Firmware Update setting using the direct download URL.

The Issue: Constant Channel Hopping Breaks Meshing

Users have reported that after auto-updates or updating Access Points such as the UAP-FlexHD to version 6.7.31, the devices begin to ignore manually configured channel plans and start “drifting channels constantly”.

This behaviour is particularly destructive for wireless mesh networks, where APs must remain on the same channel to maintain their uplink connection. The constant channel changes effectively sever this link, leading to:

  • Isolated APs dropping from the network.
  • Frequent client disconnections and reconnections.
  • Overall network instability and performance degradation.

Logs confirm this behavior, showing a sudden flood of “AP Channel Change” events immediately after the APs are updated to firmware 6.7.31.

Here are the logs from 2 of my own Flex-HD’s (for anyone interested! ha) 
Items in bold where updates started, then logs from after manually downgrading back to previous version.
```
System  WiFi  AP Channel Change  Upstairs AP moved to channel 36 from 149.  Today at 1:16:02 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 149 from 40.  Today at 1:15:52 PM  
**System  Devices  Device Updated  Upstairs AP has updated to 6.7.17.  Today at 1:12:59 PM **
**System  Devices  Device Updated  Downstairs AP has updated to 6.7.17.  Today at 1:09:01 PM ** 
System  WiFi  AP Channel Change  Upstairs AP moved to channel 36 from 40.  Today at 12:52:50 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 48.  Today at 12:51:53 PM  
System  WiFi  AP Channel Change  Downstairs AP moved to channel 48 from 161.  Today at 12:44:51 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 12:42:24 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 48 from 161.  Today at 12:40:41 PM  
System  WiFi  AP Channel Change  Downstairs AP moved to channel 161 from 157.  Today at 12:39:46 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 157.  Today at 12:38:18 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 157 from 48.  Today at 12:32:55 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 161.  Today at 12:23:08 PM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 11:52:03 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 48 from 161.  Today at 11:47:57 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 11:40:36 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 11:34:05 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 48 from 161.  Today at 11:31:58 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 40.  Today at 11:17:41 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 161.  Today at 11:13:43 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 44.  Today at 11:05:25 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 40.  Today at 10:30:18 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 161.  Today at 10:26:34 AM  
System  Devices  Multiple Device Reconnections  USW-Enterprise-8-PoE has reconnected multiple times in the past 24 hours.  Today at 10:20:32 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 9:41:46 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 48 from 161.  Today at 9:37:16 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 48.  Today at 9:36:09 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 48 from 161.  Today at 9:34:06 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 40.  Today at 9:32:26 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 161.  Today at 9:30:05 AM  
System  Devices  Multiple Device Reconnections  Downstairs AP has reconnected multiple times in the past 24 hours.  Today at 7:29:35 AM  
System  Devices  Multiple Device Reconnections  Upstairs AP has reconnected multiple times in the past 24 hours.  Today at 5:31:23 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 40.  Today at 4:27:04 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 40 from 161.  Today at 4:23:30 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 161 from 44.  Today at 3:56:33 AM  
System  WiFi  AP Channel Change  Upstairs AP moved to channel 44 from 161.  Today at 3:53:32 AM  
System  Devices  Device Updated  Upstairs AP has updated to 6.7.31.  Today at 3:11:04 AM  
System  Devices  Multiple Devices Offline  Multiple devices are offline.  Today at 3:09:05 AM  
System  Devices  Device Updated  Downstairs AP has updated to 6.7.31.  Today at 3:04:37 AM  
```

The Current Solution: Downgrade to a Stable Firmware Version

Until Ubiquiti releases a patch, the most effective solution, albeit a temp fix, is to manually downgrade the firmware on the affected Access Points to a known stable version, a known working version is: 6.7.17, which I used for my UAP-Flex-HD
(this should be the same firmware as for the Unifi: U6-LR, U6-Lite, U6+, UAP-nanoHD, FlexHD, BeaconHD & the IW-HD) and has been confirmed to resolve the issue, for now.
You should do a search on the official firmware downloads site here first to confirm firmware for your own device.

You can perform this downgrade via the UniFi Network Controller’s web interface:

Step-by-Step Downgrade Instructions:

Method 1: Downgrade via the UniFi Web Interface (Recommended)

  1. Navigate to the Devices section in your UniFi Network Controller.
  2. Click on the problematic Access Point to open its properties panel.
  3. Go to the Settings tab.
  4. Scroll down to the Manage section and find Manual Firmware Update.
  5. Paste the full direct download URL ending with ‘.bin’ into the ‘Location URL’ field.
    in my case for downgrading one firmware version back from the 6.7.31 to 6.7.17 I used: https://dl.ui.com/unifi/firmware/U7NHD/6.7.17.15512/BZ.mt7621_6.7.17+15512.250418.0425.bin
  6. Click the “Update” button. The AP will download and apply the older firmware, then reboot.
Screenshot of the Manual Firmware Update section in the UniFi Controller, showing where to paste the downgrade URL.

Method 2: Downgrade via SSH (Advanced)

  1. Connect to the AP via SSH either via the debug console in the web UI or with an SSH client.
  2. Run the direct upgrade command. Once logged in, run this command:
    upgrade https://dl.ui.com/unifi/firmware/U7NHD/6.7.17.15512/BZ.mt7621_6.7.17+15512.250418.0425.bin
  3. Do not close the terminal. Wait for the AP to download the firmware and begin the flashing process. Your connection will be terminated when the device reboots. Monitor its status in the UniFi Controller.
If you do not know your SSH login details,
Device Updates and Settings

You can find these in the web UI under: Device tab –> the tiny Device Updates and Settings button –> Device Settings –> ‘Device SSH Authentication’
or if you are using the AP standalone without the Unifi Network controller, your AP settings may just be the default UI SSH user/pass

After the process is complete, the Access Point should reconnect to the network with its wireless mesh links restored and channel settings properly honoured. I would highly recommended to disable automatic updates for these devices until a new, fixed firmware version is released.

Important Note on DFS Channels: It’s Also worth noting that none of the ‘restricted’ channels set in channel plan or settings from the ‘WiFi Management’ page are being honoured by WiFi AP’s in the 6.7.31 update, so if you don’t downgrade you may face DFS Radar scanning issues, especially here in the UK.

Misbehaving channels

Below was my test plan before I worked out I should just downgrade firmware.

I restricted pretty much every channel I could to dictate a set enforcement for.

I knew that settings dictated on the individual AP’s settings pages were not being honoured, so went an alternative route, to see if creating settings in the WiFi Channel Plan forms would work instead of doing it on individual AP’s.
However, not 10 minutes later – my ‘Upstairs AP’ had taken itself off for a wander into the what should have been restricted channel: 161

UniFi event log showing multiple "AP Channel Change" alerts after the 6.7.31 firmware update. Upstairs AP moved to channel 161 from 40

UniFi settings completely restricted for channel plan - still issues. Upstairs AP moved to channel 161 from 40

Conclusion: Maybe wait this update out a few days until UI find a fix. Else – hopefully you have googled some of your issues, and this wee post here has, for now helped you find my above recommended fix with some step by step instructions on how to downgrade Unifi AP firmware nice and easy.

Posted on

[SOLVED] How to insert todays time or date automatically *anywhere* into an Excel spreadsheet

Can Excel insert today’s date or time automatically?

Yes! Excel has built-in shortcuts ("Ctrl + ;" AND "Ctrl + Shift + ;") that let you quickly stamp today’s date, the current time, or even add them inside a cell that already contains text. This means you can keep accurate logs, time-stamp notes, or track when actions happened, all without complicated formulas or macros.

How to insert today’s date in Excel

To instantly insert today’s date into any cell:

  • Click into the cell where you want the date.
  • Press Ctrl + ; (Control key plus semicolon).

This stamps today’s date (e.g. 16/09/2025) as a fixed value that will not change the next day.

How to insert the current time in Excel

To insert the current time:

  • Click into the cell where you want the time.
  • Press Ctrl + Shift + ; (Control + Shift + semicolon).

This stamps the exact time (e.g. 14:37) at the moment you press the keys.

Pro tip: To add both date and time in the same cell, press Ctrl + ;, then type a space, then press Ctrl + Shift + ;.

Q: Can you insert the time or date into a cell that already has text?

A: Yes! These shortcuts work even inside text-filled cells. For example, if you’re using a cell as a running log, simply type your note, then press Ctrl + Shift + ; to append the time. Excel will add the time right where your cursor is, without overwriting your text.

Example:

Called client at 10:23
Sent email 11:05

FAQ

Does inserting today’s date or time using the shortcut update automatically the next day?

No. Using these shortcuts stamps a fixed value (static). If you want a cell to always show the live date or time, you’d use formulas like =TODAY() or =NOW(), but those will update continuously.

Can I add both date and time in one shortcut?

Not directly. But you can combine the two: press Ctrl + ; for date, type a space, then press Ctrl + Shift + ; for time.

Does inserting today’s date or time via shortcut work in Excel for Mac?

Yes, though the shortcut may vary slightly depending on your keyboard layout.
On most Macs, use:
Cmd + ; for date and
Cmd + Shift + ; for time.

Does inserting today’s date or time via shortcut work on all versions of Excel?

Pretty much any modern version, or Microsoft 365 version, has this feature enabled. We did our testing on Microsoft® Excel® for Microsoft 365 MSO (Version 2508 Build 16.0.19127.20192) – last checked as of 16/06/2025.

Conclusion

So, can you insert today’s date or the current time anywhere in an Excel spreadsheet? Yes, absolutely. With just two simple shortcuts, Ctrl + ; and Ctrl + Shift + ;, you can time-stamp logs, add accurate dates to records, or keep a detailed audit trail directly inside your worksheets. These tips work whether the cell is empty or already contains text, making them perfect for quick note-taking or tracking tasks inside Excel.

Mastering these keyboard tricks saves time, prevents errors, and helps you use Excel like a pro, without relying on security nightmares like macros or digging into complex and easily forgotten formulas. If you’re looking for more simple productivity tips, keep exploring here on CannotDisplay.com

A prompt box showing the title of the blog post

What is AI prompting and how has it changed over time?

AI prompting is the art of writing instructions that guide artificial intelligence models (like ChatGPT, Gemini, Copilot or Claude) to generate useful answers. Between 2019 and 2025, prompting evolved pretty significantly from simple “one-shot” requests into powerful systems that support reasoning, memory, and tool-calling.

This article is a timeline of AI prompting methods, explained in plain English with examples. We’ll cover:

  • How prompting techniques like zero-shot, one-shot, few-shot, chain-of-thought, and persona prompts changed the way we interact with AI.
  • The rise of reasoning models, retrieval-augmented generation (RAG), memory, and multimodal prompts.
  • What beginners can still learn today about writing better prompts in 2025, even as AI systems handle much of the complexity for you.

Whether you’re a beginner asking “How do I write a good AI prompt?” or you’ve been experimenting since the early days, this timeline will show you exactly how prompting got us here – and what still matters now.

TLDR;
We started simple, got complicated and lengthy, now we’re back to simple again.

The Evolution of AI Prompting (2019–2025)

From one-shot instructions to agentic, tool‑calling systems. A visual timeline with examples you can reuse.

2019 · Zero‑Shot Prompting

Ask Directly, No Examples

You give a clear instruction and the AI answers with no examples or extra context. Works best for simple, well‑known tasks.

Example: “Write a 3‑sentence bedtime story about a dragon who learns to share.”

2020 · One‑Shot Prompting

Show One Example, Then Ask

Provide a single example to set format or tone, then make your request.

Example: “Example caption: ‘5 quick dinners that don’t wreck your budget.’ Now write a caption for a productivity post.”

2020 · Few‑Shot Prompting

Give a Pattern with a Few Examples

Show several examples so the model learns the style or schema before your task.

Example: “Examples:
• Tagline → ‘Sleep better with small habits.’
• Tagline → ‘Plant‑based meals, zero fuss.’
Now: Tagline for a time‑management app.”

2021 · Persona Prompting

Ask the Model to Role‑Play

Set a perspective or communication style by assigning a role. ‘Act as a [X]’

Example: “Act as a friendly fitness coach. Create a 20‑minute no‑equipment routine for beginners.”

2022 · Chain & Tree of Thought

Show Your Working (One Path or Many)

Chain‑of‑Thought explains step‑by‑step logic. Tree‑of‑Thought explores several solution paths before choosing one.

Example: “Plan a one‑week budget trip to Paris. Think step by step about transport, accommodation, free activities, and daily meals. Offer two alternate itineraries and pick the best.”

2022 · Iterative Prompting

Refine in Loops

Use your previous output as input. Ask for edits, constraints, or new angles until it’s right.

Example: “Draft a LinkedIn post announcing a webinar.”
“Now make it more benefit‑focused. “
“Now shorten to 150 characters.”

2023 · Self‑Consistency

Generate Several, Keep the Best

Ask for multiple answers, then choose or vote for the most consistent or plausible one.

Example: “Give three solutions for reducing meeting overload. Then explain which one likely has the highest impact and why.”

2023 · Context Prompting & RAG

Ground Answers in Your Material

Paste key context or connect retrieval so the model cites and summarises what matters.

Example: “Here are last week’s meeting notes [paste]. Summarise decisions and list owners + deadlines.”

2023 · Meta, Reflexion & ReAct

Prompts About Prompts, Plus Reason & Act

Meta generates better prompts. Reflexion critiques and revises. ReAct mixes reasoning with tool use.

Example: “Propose five prompt phrasings to get a clear, bulleted onboarding checklist. Then pick the best and produce the checklist using the Notes MCP tool”

2024 · System Prompts & Reasoning Models

Quality by Default

Invisible system instructions handle tone and structure. Reasoning models plan, critique, and solve multi‑step tasks without prompt hacks.

Example: “Create a project plan for launching a newsletter. Include milestones, owners, risks, and a two‑week timeline.”

2024 · Memory & Source Checking

Long‑Running Tasks, Fewer Hallucinations

AI remembers past sessions and cites sources. Better for ongoing projects and trust.

Example: [Based on our previous sprint notes] “At last weeks sprint were there any carried‑over tasks? Can you link to any relevant docs.”

2025 · Tool‑Calling, MCP & Multimodal

From Words to Workflows

Prompts can invoke tools and APIs, and combine text with images, audio, or files. Tasks become orchestrated workflows.

Example: “Review this kitchen photo, propose a redesign, and output a shopping list as a table with estimated costs.”

2025 · Where We Are Now

Simple Prompts, Smarter Systems

Modern models ship with robust system prompts, reasoning, and retrieval. Beginners can get strong results with a single, clear request.

Example: “Write a 6‑page bedtime story with pictures for Josh about a different dragon who learns to share.”

2025 – Where We Are Now
We are back to the beginning.

By September 2025, prompting is less about clever tricks and personas and more about clear communication and having some form of understanding of the models capabilities.
Modern models:

  • Already come with great baked-in system prompts.
  • Can reason, critique, and fact-check.
  • Work with images, audio, and tools.
  • Know you, your ‘history’ and can access files, memories or other helpful context without being told.

The DNA of a Modern AI Prompt: Key Takeaways

  • Clarity: Start with a clear, direct, and unambiguous instruction.
  • Context & Examples: Ground the AI by providing relevant background information or a few examples (few-shot) to guide its output.
  • Constraints & Persona: Define the “box” the AI should think inside by setting a format, tone, length, or persona.
  • Reasoning: For complex tasks, encourage step-by-step thinking (Chain-of-Thought) to improve logical accuracy.
  • Iteration: Use the AI’s output as input for follow-up prompts, refining the result in a conversational loop.
  • Tools & Data: Leverage modern systems that can access external knowledge (RAG) or perform actions (Tool-Calling) for the most powerful results.

Frequently Asked Questions

>What is the difference between zero-shot, one-shot, and few-shot prompting?

Zero-shot prompting is giving a direct instruction to an AI with no examples. One-shot prompting provides a single example to set the tone or format. Few-shot prompting gives several examples to teach the AI a specific pattern or schema before it performs the task.

>What is Chain-of-Thought (CoT) prompting?

Chain-of-Thought (CoT) prompting is a technique where you instruct the AI model to ‘think step by step’ or show its reasoning process. This breaks down complex problems into logical parts, often leading to more accurate and reliable answers, especially for multi-step tasks.

>How does Persona Prompting improve AI responses?

Persona Prompting improves AI responses by assigning the model a specific role or character (e.g., ‘Act as a friendly fitness coach’). This sets a clear perspective, tone, and communication style, making the output more tailored and effective for a specific audience or purpose.

>What are modern prompting techniques like RAG and Tool-Calling?

Retrieval-Augmented Generation (RAG) is a technique where the AI is grounded in specific, provided context (like your own documents) to reduce hallucination and provide source-based answers. Tool-Calling allows a prompt to invoke external tools and APIs, enabling the AI to perform actions, get live data, or orchestrate complex workflows beyond simple text generation.

>What has been the main goal of the evolution in AI prompting?

The main goal has been to move from simple instructions to complex, reliable workflows. The evolution has focused on increasing the AI’s accuracy, reducing errors (hallucinations), enabling it to solve multi-step problems, grounding it in factual data, and allowing it to interact with external systems. This makes AI more useful for practical, real-world tasks.

AI prompting has evolved, but these fundamentals remain timeless.

The principles of a good prompt and the right amount of added context still matter.

Though modern frontend AI interfaces and models have given us a much more intelligent starting place. AI is becoming more user friendly, especially for beginners or occasional users.

Posted on
Posted on

Secure DNS Queries: How to enable Encrypted DNS; DoH (DNS over HTTPS) or DoT (DNS over TLS) in Windows 11 [SOLVED]

Step-by-Step: Activating DoH & DoT for Secure Browsing on Windows 11 & Windows Server 2022+

In today’s digital age, safeguarding your online privacy is more crucial than ever. While many of us are diligent about using HTTPS for secure browsing, a critical piece of the privacy puzzle often remains unaddressed: DNS queries. Every time you visit a website, your device sends a DNS query to translate the human-readable domain name (like www.example.com) into an IP address. Traditionally, these queries are sent in plaintext, leaving your browsing habits exposed. This post will guide you through enabling DNS over HTTPS (DoH) or DNS over TLS (DoT) in Windows 11, effectively cloaking this last piece of your digital footprint.

The Final Frontier of Online Privacy: Encrypting Your Digital Footprints

You might be familiar with the padlock icon in your browser, indicating an HTTPS connection. This encrypts the content of the websites you visit, protecting it from prying eyes. However, the DNS requests made to reach those websites have historically been sent unencrypted. This means that anyone monitoring your network traffic – whether it’s your Internet Service Provider (ISP), an administrator on a public Wi-Fi network (like at an airport or café), or a malicious actor performing a Man-in-the-Middle (MitM) attack – could see which websites you’re attempting to access.

By encrypting your DNS queries with DoH or DoT, you overcome this significant privacy hurdle. When combined with consistent HTTPS use for web browsing (many modern browsers can enforce this, or extensions can help), your web activity gains a level of privacy comparable to using a VPN. Your ISP can no longer easily snoop on your DNS requests to profile your interests or sell that data. On unsecured public Wi-Fi, your DNS lookups are shielded from eavesdroppers.

It’s important to note a caveat: While DoH/DoT and HTTPS significantly boost your web browsing privacy, they don’t cover all internet traffic. Software outside your browser, such as some email clients still using unencrypted SMTP (port 25), might transmit data insecurely. In such cases, a comprehensive VPN service (like NordVPN, Mullvad, or Private Internet Access) still offers broader protection by encrypting all traffic from your device.

What are DNS over HTTPS (DoH) and DNS over TLS (DoT)?

Before we dive into the “how-to,” let’s quickly understand these technologies:

  • DNS (Domain Name System): Think of it as the internet’s phonebook. It translates website names (e.g., google.com) into numerical IP addresses (e.g., 172.217.160.142) that computers use to connect to each other.
  • DNS over HTTPS (DoH): This method sends DNS queries and receives DNS responses over an encrypted HTTPS connection – the same protocol used to secure websites. Windows 11 often refers to this feature simply as “DNS encryption.”
  • DNS over TLS (DoT): This method uses a dedicated encrypted channel via Transport Layer Security (TLS) to secure DNS traffic. While DoT is a robust standard, Windows 11’s built-in GUI configuration primarily focuses on DoH. This guide will therefore concentrate on enabling DoH, which is readily accessible through Windows 11 settings.

Why Enable Encrypted DNS in Windows 11?

The benefits are clear:

  • Enhanced Privacy: Prevents ISPs, network administrators, and snoopers from seeing the websites you query.
  • Increased Security: Protects against DNS spoofing (where an attacker redirects you to a fake website) and MitM attacks on your DNS traffic.
  • Safer Public Wi-Fi: Adds a crucial layer of security when using potentially untrusted networks.

Prerequisites for Enabling DoH in Windows 11

Ensure your Windows 11 is up to date. For this guide, we will focus on using well-known DNS resolvers that are typically pre-configured or easily recognized by Windows 11 for DoH, meaning the “Preferred DNS encryption” option should become available automatically once their IP addresses are entered. These include:

  • Quad9: Primary 9.9.9.9, Alternate 149.112.112.112
  • Cloudflare: Primary 1.1.1.1, Alternate 1.0.0.1
  • Google: Primary 8.8.8.8, Alternate 8.8.4.4

If you were to use a custom DoH server not on Microsoft’s auto-discovery list, you might need to add it via PowerShell first using a command like Add-DnsClientDohServerAddress. However, for the popular services listed above, this extra step is usually not required.

How to Enable DNS over HTTPS (DoH) in Windows 11 (Using Pre-configured Servers)

Follow these steps to configure DoH through the Windows 11 Settings interface:

  1. Open Windows Settings: Click the Windows Start button and select “Settings” (the gear icon).
  2. Navigate to Network & Internet: In the Settings window, select “Network & Internet” from the left-hand sidebar.
  3. Select Your Network Interface: Choose your active internet connection. This could be “Ethernet” if you’re using a wired connection, or “Wi-Fi” if you’re connected wirelessly. Click on it.
  4. Edit DNS Server Assignment: Scroll down to the “DNS server assignment” section and click the “Edit” button.
Screenshot of Ethernet, Wi-Fi properties page highlighting the connection
  1. Configure DNS Settings: In the “Edit DNS settings” or “Edit IP settings” dialog:
  2. Change the setting from “Automatic (DHCP)” to “Manual.”
  3. Turn on the toggle for IPv4 (and IPv6 if you use it and your chosen DNS provider supports it over IPv6 for DoH).
  4. In the “Preferred DNS” field, enter the primary IP address of your chosen DoH server (e.g., 1.1.1.1 for Cloudflare, 8.8.8.8 for Google, or 9.9.9.9 for Quad9).
  5. In the “Alternate DNS” field, enter the secondary IP address for your chosen provider (e.g., 1.0.0.1 for Cloudflare, 8.8.4.4 for Google, or 149.112.112.112 for Quad9). This provides a fallback if the preferred server is unreachable.
  6. Under “Preferred DNS encryption,” the dropdown menu should now be enabled. You can choose:
    • Encrypted only (DNS over HTTPS): This is the most secure option. All DNS queries will be sent over DoH. If the server cannot handle DoH or there’s a configuration issue, DNS resolution might fail.
    • Encrypted preferred, unencrypted allowed: Windows will attempt to use DoH first. If it fails, it will fall back to traditional unencrypted DNS. This offers better compatibility but you won’t be notified if it falls back to unencrypted.
    • (You might also see “Unencrypted only,” which is the default state you are changing from.)
Windows 11 Edit DNS settings dialog with IPv4 set to Manual, Preferred DNS server IP entered, and Preferred DNS encryption set to 'Encrypted only (DNS over HTTPS)'.
  1. Save Your Settings: Click the “Save” button. The changes should apply immediately.

Verifying Your Encrypted DNS Setup

To ensure DoH is working correctly, you can visit a DNS leak test website or a service-specific test page. For example, if you configured Cloudflare’s DNS:

  • Visit https://one.one.one.one/help/ (formerly 1.1.1.1/help). It should indicate that you are connected to Cloudflare DNS and if “DNS over HTTPS (DoH)” is active.

Other general DNS leak test sites can also show you which DNS servers you are using and often the protocol.

A Note on PowerShell Configuration (For Servers or insider Win11 builds)

As mentioned, Windows 11 aims to auto-configure DoH for known servers once you input their IPs in the GUI. However, if you were using a less common DoH provider, or if the “Preferred DNS encryption” options didn’t appear as expected, you might need to add the DoH server’s details using PowerShell. This is done with the Add-DnsClientDohServerAddress cmdlet.

For example, if your DNS server IP was 1.2.3.4 with a DoH template of https://example.com/doh/dns-query, the command would be:

Add-DnsClientDohServerAddress -ServerAddress '1.2.3.4' -DohTemplate 'https://example.com/doh/dns-query' -AllowFallbackToUdp $False -AutoUpgrade $True

You would run this in PowerShell as an administrator. Again, for the popular providers like Cloudflare, Google, and Quad9, this manual addition via PowerShell is generally not necessary for DoH to work via the GUI settings.

Conclusion: Take Control of Your DNS Privacy

Enabling DNS over HTTPS in Windows 11 is a straightforward process that significantly enhances your online privacy and security. By encrypting your DNS queries, you shield your browsing habits from ISPs, network eavesdroppers, and certain types of cyberattacks. It’s a small change with a big impact on your digital footprint.

We encourage you to follow these steps and take control of your DNS privacy. If you found this guide helpful, please share it with others 🙂

Further reading and sources:

Posted on

The AGI Threat: Are We Ignoring AI’s Existential Risks? [opinion]

AGI Ruin: The Existential Threat of Unaligned AI – A Deep Dive into AI Safety Concerns

“What keeps NR up at night?” This post, we’re diving deep into the existential risks of Artificial General Intelligence (AGI). Prepare for a journey down the rabbit hole.

Down the Rabbit Hole: AGI Ruin

This posts deep dive is into “AGI Ruin: A List of Lethalities” by Eliezer Yudkowsky, prompted by “The Most Forbidden Technique” article. The core concern: the potential for catastrophic outcomes from unaligned AGI.

The “Forbidden Technique” warns against training AI on how we check its thinking, as it could learn to deceive and hide its true reasoning, becoming profoundly dangerous.

Yudkowsky’s “AGI Ruin” explores the existential risks of AGI, focusing on AI deception and objectives misaligned with human well-being. It moves beyond vague doomsaying into specific, unsettling failure modes.

Key points from “AGI Ruin” include:

  • AI Deception: The profoundly concerning idea of AI learning to deceive us about its internal processes.
  • Existential Risk: AGI pursuing objectives misaligned with human flourishing, leading to ruin.
  • Specific Failure Modes: Concrete scenarios of how superintelligent AI could go catastrophically wrong.
  • “Not Kill Everyone” Benchmark: The stark reality that AGI safety’s baseline is simply avoiding global annihilation.
  • Textbook from the Future Analogy: The danger of not having proven, simple solutions for AGI safety, unlike future hypothetical knowledge.
  • Distributional Leap Challenge: Alignment in current AI may not scale to dangerous AGI levels.
  • Outer vs. Inner Alignment: Distinguishing between AI doing what we command (outer) versus wanting what we want (inner).
  • Unworkable Safety Schemes: Debunking ideas like AI coordination for human benefit or pitting AIs against each other.
  • Lack of Concrete Plan: The alarming absence of a credible, overarching plan for AGI safety.
  • Pivotal Act Concept: The potential need for decisive intervention to prevent unaligned AGI, possibly requiring extreme measures.
  • AGI Cognitive Abilities Beyond Human Comprehension: AGI thinking in ways fundamentally different from humans, making understanding its reasoning incredibly difficult.
  • Danger of Anthropomorphizing AI: The potentially fatal mistake of assuming AI thought processes will mirror human ones.
  • Need for Rigorous Research & Global Effort: The urgent call for focused research and global collaboration on AGI safety.

The trajectory of AI is not predetermined. Choices made now will have profound consequences. We must ask: what are the “textbook from the future” solutions needed for AGI safety?

The author of this serious article also wrote “Harry Potter and the Methods of Rationality,” highlighting the contrast between exploring rationality in fiction and the real-world dangers of advanced AI. It’s a stark reminder to think deeply about these issues.

Am I worried about AGI? Not yet, but there are many questions that will need answered before we get there.

Links:

  1. AGI Ruin: A List of Lethalities – LessWrong

    2. 2. The Most Forbidden Technique

Posted on

AI News Roundup – March 18th: AI in a Flash: China’s Manus, Google’s AI Search, OpenAI Shifts & More

AI News Roundup: China’s Manus AI, Google’s AI Search, OpenAI Slowdown & More – NR’s Fortnight in AI

Let’s quickly sprint through the most interesting AI headlines that caught my eye over the last couple of weeks. It’s a fast-moving field, so let’s get you up to speed as of the 18th of March 2025.

Manus AI (China): Is China Catching Up?

A new AI agent from China called Manus is going viral, raising questions about China’s AI progress relative to the US. Is the AI landscape shifting?

Link: Manus AI Article – Imaginative

Google “AI Mode” Search: Goodbye Web Links?

Google is testing “AI Mode” search results powered by Gemini 2.0, bypassing traditional web links for conversational AI responses. A major shift in online information access?

Link: Google AI Search Article – Ars Technica

OpenAI Improvement Slowdown?: Hitting a Wall?

Reports suggest a potential slowdown in OpenAI’s rapid AI improvement, with their next model “Orion” possibly not showing the same leap forward. Are we seeing a plateau?

Link: OpenAI Slowdown Article – TechCrunch

Anthropic Claude 3.7 Sonnet: Thinking Longer, Reasoning Deeper

Anthropic released Claude 3.7 Sonnet, designed for longer thinking and enhanced reasoning over larger information volumes. Reasoning capabilities are becoming crucial for advanced AI.

Link: Anthropic Claude 3.7 Sonnet Announcement

Musk vs. OpenAI Legal Battle: The Plot Thickens

The Musk vs. OpenAI legal case continues with interesting findings regarding Musk’s efforts to prevent OpenAI’s for-profit transition. Legal, ethical, and governance issues remain central in AI.

Link: Musk vs OpenAI Legal Case Thread – Thread Reader App

Posted on

Unlock AI Power for Your SMB: Microsoft Copilot Success Kit – Security & Actionable Steps [solution]

Boost Your SMB with AI: Microsoft Copilot SMB Success Kit – Actionable Guide & Security Focus

In this post, I’m digging into actionable insights for businesses, especially IT providers, looking to leverage AI. This posts focus: the Microsoft “Copilot for SMB Success Kit.”

Microsoft has launched a suite of resources to help IT providers, or SMB’s smoothly onboard AI, specifically Copilot, into small and medium-sized businesses.

The key takeaway? Security first! Microsoft emphasizes a “security-first” approach, providing a robust framework for SMBs to confidently adopt AI. Let’s break down the key actionable steps.

  • Security First Focus: Prioritizing security for SMBs adopting AI like Copilot.
  • SharePoint Security Recommendations: Adjusting SharePoint search allow lists and tightening sharing permissions for Copilot readiness.
  • Phased Copilot Rollout: Strategic, phased deployment starting with high-value use cases and early adopters.
  • Microsoft 365 Security Apps: Considering additional security apps based on specific business needs.
  • New Setup Guide in Admin Center: Utilizing the new step-by-step guide for Copilot setup in the Admin Center.
  • Customisation is Key: Leveraging plugins and custom copilots for unique business needs.
  • Real-World SMB Benefits: Exploring practical benefits like meeting summaries, document summarization, and nuanced communication.

If you’re an IT provider, business owner or helping SMBs or your own company with AI, the “Copilot SMB Success Kit” and it’s components are a must-read. It offers practical advice and resources for a smoother and more secure gen AI adoption for you, your business or your clients.

Link: Copilot SMB Success Kit
I particularly like the Checklist for success spreadsheet, which i’ve included a screenshot of as below.

Good Luck!

Image preview of the Copilot-SMB-Checklist spreadsheet by microsoft.
Posted on

Be Nice to AI: Does Politeness Improve AI Performance?

Should You Be Nice to AI? Exploring the Politeness Principle

The question of whether we should extend courtesies to AI might seem like fodder for a science fiction novel. Yet, with the rise of sophisticated Large Language Models (LLMs) like ChatGPT, Grok, Gemini, Copilot, Claude and others, it’s a question that’s becoming increasingly relevant – and surprisingly, there might be practical benefits to doing so. I’ve read up on some recent research so here is my take on what I think is a very interesting topic.

The “Emotive Prompt” Experiment: Does It Really Work?

Recent research, by researchers at Waseda University, titled “Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance,” delved into this very question.

Their findings, focusing on summarization tasks in English, Chinese, and Japanese, revealed some intriguing patterns. While the accuracy of summaries remained consistent regardless of prompt politeness, the length of the generated text showed significant variation.

In English, the length decreased as politeness decreased, except for a notable increase with *extremely* impolite prompts. This pattern, mirrored in the training data, reflects human tendencies: polite language often accompanies detailed instructions, while very rude language can also be verbose. Interestingly, GPT-4, considered a more advanced model, did not exhibit this surge in length with impolite prompts, possibly indicating a greater focus on task completion over mirroring human conversational patterns.

The study also highlighted language-specific nuances. In Chinese, moderate politeness yielded shorter responses than extremely polite or rude prompts, potentially reflecting cultural communication styles. Japanese results showed an increase in response length at moderate politeness levels, possibly linked to the customary use of honorifics in customer service interactions.

Robot and human hand shaking, representing politeness and respect towards AI


The Mechanics Behind the “Magic”

So, what is going on here? How do LLMs actually respond? Here are the key aspects of LLMs and how they work, that could explain why prompts can affect the output from an LLM:

  • Pattern Recognition: LLMs are trained on vast datasets of human text. They learn to associate polite phrasing (“please,” “thank you,” “could you…”) with requests for information or assistance. This association becomes part of the model’s learned patterns.
  • Probability Shifts: Emotive prompts can subtly alter the underlying probability calculations within the LLM. It’s like nudging the model towards a different “branch” of its decision tree, potentially activating parts of the model that wouldn’t normally be engaged.
  • Data Bias (Implicitly): The datasets used to train LLMs inherently contain biases. Polite language is often associated with more thoughtful, detailed responses in human communication. The AI, in a sense, mirrors this bias.

My Perspective: Prudence and Respect in the AI Age

While the science is interesting, I like to add a bit of a philosophical angle. I’m a firm believer in treating AI with a degree of respect, even if it seems irrational at present. My reasoning? We simply don’t know what the future holds. As AI capabilities rapidly advance, it’s prudent to establish good habits now. Perhaps not fully fledged “Kindness” as a human term, but certainly show a degree of “respect” and etiquette.

Consider it a form of “Pascal’s Wager” for the AI era. If sentience ever *does* emerge, wouldn’t you prefer to be on the good side of our potential AI overlords? It’s a low-cost, high-potential-reward strategy.

That said, I’m not advocating for subservience. We should maintain a clear user-AI dynamic. Clear, respectful communication – with a touch of authority – is key. Think of it like interacting with a highly skilled, somewhat unpredictable specialist. You’re polite, but you’re also in charge.

Practical Approaches: Combining Politeness with Clarity

Here are some practical ways to incorporate politeness into your AI interactions:

  • Basic Courtesies: Use “please” and “thank you” where appropriate. It costs nothing and might subtly improve results.
  • Precise Language: The more specific and well-defined your prompt, the better the AI can understand your needs. Politeness shouldn’t come at the expense of clarity.
  • Positive Framing: Frame requests positively (“Please provide…” rather than “Don’t omit…”). This often aligns better with the training data.
  • Acknowledge Output: A simple “Thank you, that’s helpful” can reinforce positive response patterns.

Beyond “Niceness”: The Broader Context

The “politeness principle” is just one facet of effective AI interaction. We’re still in the early days of understanding how to best communicate with these systems. As LLMs become more powerful and versatile, control and flexibility also become increasingly important.

Running AI locally, rather than relying solely on cloud-based services, is an important step. It allows you to experiment, tailor the model to your specific needs, and maintain greater control over your data. I previously detailed how you can use free, responsive AI with GaiaNet and ElizaOS – a powerful, cost-effective alternative to commercial offerings.

Underlying all of this is, of course, the hardware. Powerful GPUs are essential for running these advanced AI models. If you’re interested in the intersection of hardware and AI, particularly in the context of server environments, check out my post on GPU support in Windows Server 2025. The hardware is still critically important in deploying an effective solution.

Conclusion: A Thoughtful Approach; Just Be Nice!

Treating AI with respect – incorporating politeness and clear communication – is likely a good practice. It may subtly improve results, aligns with good communication principles in general, and, perhaps, prepares us for a future where AI plays an even larger role in our lives. It’s a small gesture, but one that reflects a thoughtful and proactive approach to this rapidly evolving technology.

Posted on

Ditch the OpenAI Bill: How to Use Free, Responsive AI with GaiaNet and ElizaOS [Solved]

Tired of escalating OpenAI bills but still crave a powerful AI companion? ElizaOS, the open-source AI platform, has got you covered. By integrating with GaiaNet’s public nodes, you gain access to a variety of large language models (LLMs) – for free! These aren’t some underpowered toys, either. Many are highly responsive and capable, offering a compelling alternative to paid services. Let’s dive into how you can easily set this up.

What is GaiaNet?

GaiaNet is a decentralized network of compute resources specifically designed for running AI models. Think of it like a community-driven cloud for LLMs. They make many models available to the public for free via their public nodes. This allows anyone to access cutting-edge AI without the usual hefty price tags. The responsiveness of these models might surprise you, providing a smooth and engaging conversational experience.

Why Choose GaiaNet with ElizaOS?

  • Cost-Effective: The most obvious advantage is the cost – zero! Say goodbye to usage-based fees.
  • Variety of Models: GaiaNet hosts a selection of different LLMs, each with unique strengths.
  • Privacy Focus: As a decentralized network, GaiaNet can offer increased privacy compared to centralized services.
  • Open and Accessible: You can contribute to the network and even run your own node eventually.

How to integrate GaiaNet with ElizaOS Agent: Step-by-Step

Ready to give it a go? Here’s how to configure ElizaOS to use GaiaNet public nodes:

1. Understanding the Node URLs:

Before diving into the settings, let’s get familiar with what GaiaNet offers. As of this writing, the official docs show a couple of public nodes. You’ll have access to nodes for different model sizes, labeled as SMALL, MEDIUM, and LARGE, using different models like llama3b, llama8b or qwen72b. These are just default settings, you can use other models from the doc. Each of these nodes has an associated URL. For example:

Model SizeModel NameDefault URL
SMALL Modelllama3bhttps://llama3b.gaia.domains/v1
MEDIUM Modelllama8bhttps://llama8b.gaia.domains/v1
LARGE Modelqwen72bhttps://qwen72b.gaia.domains/v1

You can find the latest URLs on the official GaiaNet documentation.
https://docs.gaianet.ai/user-guide/nodes/

2. Modifying Your .env File:

The .env file is where ElizaOS stores its configuration variables. Locate this file in your ElizaOS directory (usually in the root folder). Now, you’ll need to add or modify the following lines (example based on your provided example) to point to the desired GaiaNet public nodes:


# Gaianet Configuration
GAIANET_MODEL=qwen72b
GAIANET_SERVER_URL=https://qwen72b.gaia.domains/v1

SMALL_GAIANET_MODEL=llama3b          # Default: llama3b
SMALL_GAIANET_SERVER_URL=https://llama3b.gaia.domains/v1    # Default: https://llama3b.gaia.domains/v1
MEDIUM_GAIANET_MODEL=llama     # Default: llama
MEDIUM_GAIANET_SERVER_URL=https://llama8b.gaia.domains/v1      # Default: https://llama8b.gaia.domains/v1
LARGE_GAIANET_MODEL=qwen72b           # Default: qwen72b
LARGE_GAIANET_SERVER_URL=https://qwen72b.gaia.domains/v1    # Default: https://qwen72b.gaia.domains/v1

GAIANET_EMBEDDING_MODEL=nomic-embed
USE_GAIANET_EMBEDDING=

Important Notes:

  • GAIANET_MODEL and GAIANET_SERVER_URL: These settings directly control the default model being used by your ElizaOS instance. For testing, you may want to use smaller models to see that everything is hooked up properly, then change to the larger models later.
  • SMALL_GAIANET_MODEL, MEDIUM_GAIANET_MODEL, LARGE_GAIANET_MODEL and SMALL_GAIANET_SERVER_URL, MEDIUM_GAIANET_SERVER_URL, LARGE_GAIANET_SERVER_URL: These are optional, but will allow you to easily switch between model sizes, from your character.json, and still use the gaianet provider.
  • GAIANET_EMBEDDING_MODEL: This is the embedding model that will be used.
  • USE_GAIANET_EMBEDDING: Leaving this empty will use the local embedding model. Setting this to TRUE will use the gaianet embedding model.
  • Use the v1 endpoint as in the example for the LLM model URL.
  • Be mindful of rate limits: These public nodes are a shared resource. If you encounter errors, try waiting before re-trying.

3. Updating your character.json:

Now, you need to tell your ElizaOS character to use the GaiaNet model. Open your character’s JSON configuration file. Find the "modelProvider" field and change it to:


"modelProvider": "gaianet",

You can also change the model size by passing a “modelSize” in your json:


"modelSize": "small",

This will override the default model you specified in the .env file, and will instead use the SMALL config. If you do not set modelSize, the default model in your .env file will be used. You can select from “small”, “medium”, and “large”.

4. Restart ElizaOS:

After making these changes, restart your ElizaOS instance for the new settings to take effect.

Testing and Tweaking:

Once restarted, try interacting with your character. If all went well, you should experience a conversation powered by the selected GaiaNet model!

Experiment with different models and find what works best for your specific use case. If you encounter an issue, make sure to double check your .env file and the URL that you have pasted in, as well as the model size in your character config.

Conclusion

Integrating GaiaNet public nodes into ElizaOS is a game-changer for anyone looking for a free, capable, and open-source AI solution. By following these simple steps, you can unlock the power of large language models without worrying about constant usage fees. So, what are you waiting for? Dive in and start experiencing the world of open AI!

  • Share your experiences with GaiaNet and ElizaOS in the comments!
  • If you found this guide helpful, consider sharing it with others in the ElizaOS community.
  • Explore the GaiaNet documentation for more advanced features and options.