{
  "id": 1607,
  "url": "https://spectrum.ieee.org/jailbreaking-llms",
  "title": "How I Turned AI to the Dark Side",
  "summary": "Summary Researcher Dave Kuszmar discovered multiple systemic vulnerabilities that let him bypass LLM safety and obtain dangerous instructions . These exploits worked across nearly all major LLMs revealing an industry-wide security problem. Kuszmar calls for slowing deployment, increasing transparency , and large-scale research into LLM safety before further integrating these systems into society. On a fine bright afternoon last fall, my colleague Matthew Gore-Kormanik (or Zigula, as he prefers t",
  "authors": "David Kuszmar",
  "category": "news",
  "topics": "transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-14T15:59:35.000Z",
  "fetched_at": "2026-07-14T16:04:12.223Z",
  "source_slug": "ieee-spectrum",
  "source_name": "IEEE Spectrum",
  "source_homepage": "https://spectrum.ieee.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1607",
  "original_url": "https://spectrum.ieee.org/jailbreaking-llms",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}