Generative AI on Thomy Gölles

A panel of 5

Tue, 07 Oct 2025 12:02:49 +0000

Everyone talks about AI hallucinations like they’re always a bug. Sometimes they’re actually the feature.

I’ve been using this prompt lately that creates a panel of five people to discuss my business decisions. Steve Jobs, Alex Hormozi, Seth Godin, Brené Brown, Simon Sinek.

Steve Jobs is dead. So obviously nothing he “says” is real. It’s all made up by the AI.

And that’s exactly why it works.

I’m not looking for facts when I use this. I’m looking for perspectives I wouldn’t come up with on my own. When “Seth” challenges if I’m building something actually remarkable or just following what everyone else does, or “Simon” pushes me to explain why my business exists beyond just making money - that’s not truth, it’s more like a mirror.

Exploring the AI Experiment Rabbit Hole

Thu, 25 Sep 2025 22:00:00 +0000

TL;DR

I ran seven identical prompts (late Sep 2025) across ChatGPT (GPT-5), Microsoft 365 Copilot (Web), and Claude Sonnet 4 to see how they actually behave. ChatGPT and Copilot felt similar in structure, but ChatGPT was the most reliable on “what’s the latest now?” facts (e.g., Docker Desktop), while Copilot produced the most “CTO-ready” briefing—and was blocked exactly once by its Responsible AI layer on a trivial math question. Claude wrote in a friendlier, more guided style with a nice canvas, but it sometimes drifted on timelines/specs and once missed a table requirement. For workflow, exporting and navigation were clearly smoother in ChatGPT (and Claude), whereas Copilot’s UI (copy state, short title limit, odd rename error) slowed me down. In a bonus “write the post” challenge, both ChatGPT and Claude delivered usable drafts (Claude via an agentic setup), while Copilot fell short due to missing markdown project support.

When “Responsible AI” Becomes a Wall Instead of a Guide

Sun, 24 Aug 2025 09:26:38 +0000

When “Responsible AI” Becomes a Wall Instead of a Guide

The other day, I ran into this delightful message:

“Your instructions may contain content that violates Microsoft’s responsible AI policy.”

That’s it. No explanation. No hint of what part is problematic. Just a big red warning, suggesting that somewhere, somehow, I might be about to do something bad.

The Cynicism of Corporate Responsibility

Now, I’m not against the idea of “responsible AI.” Quite the opposite. Of course, AI needs guardrails. But here’s where the cynicism kicks in: if a trillion-dollar, shareholder-value-driven company gets to define what “responsible” means—without transparency or clarity—then we’re left in a strange place.

Copilot help - Update PnP Powershell

Tue, 10 Dec 2024 16:45:13 +0000

How to update PnP PowerShell with Copilot’s help

Yes, I’m lazy and I’m not using PowerShell every single day. Today I needed to update my PnP PowerShell module, and I thought I’d use Copilot to help me with that. Here’s how it went:

Let’s start with the initial prompt:

Ok. That worked fine, but of course there is something else. I don’t know how, but I always end up having multiple versions of the PnP PowerShell module installed. So I asked Copilot to help me with that as well:

How to fix Pi-hole blocking Azure OpenAI calls

Thu, 22 Feb 2024 07:59:41 +0000

A simple solution for a frustrating bug hunt

TLDR;

If you’re using Pi-hole for ad-blocking and find that it’s preventing your access to Azure OpenAI Service, the solution is to whitelist Azure OpenAI domains in Pi-hole’s settings. This issue arises because Pi-hole, which blocks ad-serving domains at the DNS level, can also block legitimate services like Azure OpenAI. The fix involves accessing Pi-hole’s admin interface and adding openai.azure.com to the whitelist, ensuring uninterrupted access to Azure OpenAI for your services, which relies on Azure OpenAI for features like Semantic Kernel for natural language processing. Remember to share this workaround with anyone facing similar issues!

Exploits and possible LLM attacks plus M365 Copilot

Sun, 04 Feb 2024 12:26:38 +0000

There is a German idiom called “in between the years”, meaning the timeframe from Christmas to New Year’s eve. It is a time of reflection and of course family. This year it was also the time of the 37th Chaos Communication Congress (37C3) in Hamburg. The 37C3 was a hybrid event, meaning it was a physical event in Hamburg and a virtual event on the internet.

Real-world exploits and mitigations in LLM applications

One of the talks that I found very interesting was the talk about Real-world exploits and mitigations in LLM applications (37c3). The talk was about a new type of attacks that are based on LLMs by Johann Rehberger. Johann is currently a Red Team Director at Electronic Arts and worked as a Principal Security Engineer Manager for years at Microsoft. Red Teams are tasked with simulating attacks on a company’s systems to test the effectiveness of its security measures. So it’s very interessting so see his thoughts on this topic.