> Markdown version of [/videos/1464-you-are-not-my-model-anymore-understanding-llm-model-behavior?t=127](https://www.wearedevelopers.com/videos/1464-you-are-not-my-model-anymore-understanding-llm-model-behavior?t=127). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# You are not my model anymore - understanding LLM model behavior

A silent filter update once caused Microsoft Copilot to completely hide internal documents. Learn how automated evaluations and uncensored testing models protect applications from unpredictable LLM shifts.

- **Speakers:** [Andreas Erben](https://www.wearedevelopers.com/@andreas-erben)
- **Event:** World Congress 2025
- **Published:** August 20, 2025
- **Duration:** 24:11
- **URL:** https://www.wearedevelopers.com/videos/1464-you-are-not-my-model-anymore-understanding-llm-model-behavior
- **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/3252396c4ce8d102c5d94d69d262d4ae/thumbnails/thumbnail.jpg?time=129115ms

## Access

Playback and chapters for this video are available with a Free account.

## Related Moments

- [Addressing core challenges in large language model deployments](https://www.wearedevelopers.com/videos/899-creating-industry-ready-solutions-with-llm-models) (from "Creating Industry ready solutions with LLM Models")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/c1137aae2e3d45e2d96a87f795887129/thumbnails/thumbnail.jpg?time=111245ms
- [Mitigating indirect prompt injection in language models](https://www.wearedevelopers.com/videos/1957-security-in-model-context-protocol-an-analysis-of-the-owasp-mcp-top-10) (from "Security in Model Context Protocol: An Analysis of the OWASP MCP Top 10")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/5e8006fd139b890d3bbe3ce4ab3d1eaf/thumbnails/thumbnail.jpg?time=11160ms
- [Designing AI applications defensively for inevitable failures](https://www.wearedevelopers.com/videos/100069-building-the-next-generation-of-ai-developer-tools) (from "Building the next generation of AI developer tools")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/84605beada7b393b4f25327c680a42a7/thumbnails/thumbnail.jpg?time=163150ms
- [Overcoming AI hallucinations and restrictive content guardrails](https://www.wearedevelopers.com/videos/1771-ai-is-an-electric-bike-for-the-brain-stoyan-stefanov) (from "AI is an Electric Bike for the Brain - Stoyan Stefanov")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/305c5fd5c00646496ef5d1d367df3861/thumbnails/thumbnail.jpg?time=313845ms
- [Understanding the unique architecture of LLM applications](https://www.wearedevelopers.com/videos/100407-red-teaming-your-llm-app-a-hands-on-threat-model-you-can-reuse) (from "Red Teaming Your LLM App -- A Hands-On Threat Model You Can Reuse")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/11a820ca699b9e4474ed6156b27f8ec6/thumbnails/thumbnail.jpg?time=160868ms
- [Exploiting exposed language models in commercial applications](https://www.wearedevelopers.com/videos/1217-can-machines-dream-of-secure-code-emerging-ai-security-risks-in-llm-driven-developer-tools) (from "Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools")
  - **Thumbnail URL:** https://customer-goifxnzhrq3d0d54.cloudflarestream.com/6ab5730e7cd03d41957ea1fbf36d900d/thumbnails/thumbnail.jpg?time=233905ms

## Related Articles

- [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models)
- [ I Gave a Video Editor More Autonomy Than a Trading Bot. On Purpose.](https://www.wearedevelopers.com/magazine/773-i-gave-a-video-editor-more-autonomy-than-a-trading-bot-on-purpose)
- [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production)
- [WWC24 Talk - Scott Hanselman - AI: Superhero or Supervillain?](https://www.wearedevelopers.com/magazine/469-wwc24-talk-scott-hanselman-ai-superhero-or-supervillain)

## Related Jobs

- [MLOps AI Engineer](https://www.wearedevelopers.com/jobs/ext/2565312-mlops-ai-engineer) at **TeamViewer Germany GmbH,**
- [LLM Training Engineer](https://www.wearedevelopers.com/jobs/48420-llm-training-engineer) at **Sciforium**
- [ML Engineer](https://www.wearedevelopers.com/jobs/48448-ml-engineer) at **Docker, Inc.**
- [Partner Sales Director - AI Alliances - Model Providers](https://www.wearedevelopers.com/jobs/48429-partner-sales-director-ai-alliances-model-providers) at **Dynatrace**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/3652934-machine-learning-engineer) at **TWILIO**
- [Staff ML Engineer](https://www.wearedevelopers.com/jobs/48463-staff-ml-engineer) at **Docker, Inc.**