AI struggles to patch vulns without adult supervision

{
  "signal_id": "5b053da1-e6c5-b8a6-1904-bab36fdc1f4d",
  "signal_type": "news",
  "signal_subtype": "launches",
  "detected_at": "2026-08-06T19:04:30+00:00",
  "company": {
    "name": "1Password",
    "domain": "1password.com"
  },
  "data": {
    "url": "https://www.theregister.com/ai-and-ml/2026/08/06/ai-struggles-to-patch-vulns-without-adult-supervision/5284319",
    "title": "AI struggles to patch vulns without adult supervision",
    "excerpt": "AI and ML Left alone, autonomous fixes often fail to fully remediate flaws AI models may not be that good at fixing security flaws. Researchers at 1Password's Off-by-1 Labs analyzed security patches generated by two frontier models - ChatGPT 5.5 at \"medium\" effort and Claude Opus 4.8 at \"high\" effort - and found that autonomous patches cleanly fixed vulnerabilities only about a quarter of the time, while most of the remainder failed to fully remediate the flaw or introduced other problems. Keith Hoodlet, director of security research at 1Password, argues in a blog post that the results show LLM-driven security remediation still needs human review. \"Across six recently disclosed CVEs, we produced 6,080 patches using two frontier, cyber-capable reasoning models,\" Hoodlet said. \"The average success rate for generating a patch that fully resolved the vulnerability (without materially changing application behavior) was just 26.0 percent.\" Of the AI-generated patches, 20.1 percent fixed the original issue but altered application behavior (eg, changing \"allow list\" logic to \"deny list\" logic). Some 2.3 percent of the patches fixed the issue while introducing new security issues. 49.3 percent of the patches failed to fix at least one existing exploit path. And 2.2 percent both failed to fix the vulnerability while introducing a new exploit path. And among the patches in the first two...",
    "product": "FLAWED",
    "summary": "1Password's Off-by-1 Labs released a research paper and a patch evaluation harness named FLAWED to help organizations evaluate the effectiveness of their security fixes.",
    "planning": false,
    "image_url": "https://image.theregister.com/5255449.jpg?imageId=5255449&x=0&y=0&cropw=100&croph=100&panox=0&panoy=0&panow=100&panoh=100&width=1200&height=683",
    "confidence": 0.9,
    "product_data": {
      "name": "FLAWED",
      "full_text": "a patch evaluation harness under the name FLAWED",
      "fuzzy_match": false
    },
    "product_tags": [
      "security",
      "general_technology"
    ],
    "published_at": "2026-08-06T19:04:30Z",
    "article_sentence": "The authors have released a patch evaluation harness under the name FLAWED that organizations can use to evaluate the effectiveness of their security fixes."
  }
}

curl https://signals.autobound.ai/v1/signals/5b053da1-e6c5-b8a6-1904-bab36fdc1f4d \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"1password.com","limit":20}'