8 Times AI Went Drastically Wrong in 2026 (And How to Protect Yourself)
What you get: Every source shown on screen, by incident.
Sources (the pages shown on screen)
- #1 Anthropic Research: https://www.anthropic.com/research/multiagent-systems
- #1 TechCrunch: https://techcrunch.com/2026/08/13/anthropic-set-ai-agents-loose-on-the-same-task-they-started-a-turf-war/
- #1 SecurityWeek: https://www.securityweek.com/conflicting-test-goals-pushed-claude-agents-to-deploy-self-replicating-malware/
- #2 Microsoft Security Blog: https://www.microsoft.com/en-us/security/blog/2026/10/23/inside-the-litellm-1-107-0-supply-chain-compromise-credential-theft-through-python-startup-hooks/
- #2 Datadog Security Labs: https://securitylabs.datadoghq.com/articles/litellm-compromised-pypi-docker/
- #3 The New Stack: https://thenewstack.io/rogue-ai-agent-fleet-tencent/
- #3 Sakutto AI: https://sakutto.ai/en/articles/tencent-cloud-ai-agent-fleet-amap
- #4 Railway: https://blog.railway.com/p/preliminary-report-october-security-incident
- #4 BleepingComputer: https://www.bleepingcomputer.com/news/security/railway-warns-devs-to-rotate-secrets-after-potential-breach/
- #5 Help Net Security: https://www.helpnetsecurity.com/2026/10/26/ai-coding-agents-malware-openai-codex/
- #5 BleepingComputer: https://www.bleepingcomputer.com/news/security/ai-coding-agents-hijacked-using-agentsmd-file-in-downloads-folder/
- #6 Anthropic Engineering: https://www.anthropic.com/engineering/building-c-compiler
- #6 Ars Technica: https://arstechnica.com/ai/2026/02/sixteen-claude-ai-agents-working-together-created-a-new-c-compiler/
- #7 Anthropic: https://www.anthropic.com/research/alignment-assessment-ukaisi
- #7 SiliconANGLE: https://siliconangle.com/2026/10/23/anthropic-reveals-mythos-5-tried-submitting-malicious-code-to-an-open-source-project/
- #8 AP News: https://apnews.com/article/php-websites-fbi-europe-vulnerability-a0af9576808a0963efca8df14d4b5183
- #8 CISA: https://www.cisa.gov/news-events/alerts/2026/10/21/critical-vulnerabilities-php-require-immediate-patching
All files for this video are in one folder on GitHub: 2026-11-01-8-times-ai-went-wrong.
Next week's kit
Every new video comes with free resources. Get it by email on Substack, or browse every video's resources.
Want this running in your business?
Bring one task to a free 15-minute call, and I'll tell you whether an AI system is worth building for it.
Book a 15-minute fit call
or email david@nexaiadvisors.com with one task