Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
Large Language Models
A large language model (LLM) is an AI system trained on written text to predict and generate human language.
Bottom line
They are described as developed by vendors including OpenAI and, among others, Anthropic, Google, Meta and xAI.12
Why it matters. For a security and policy audience, large language models carry reported vulnerability classes including prompt injection and hallucination that affect downstream products,45 and their outputs have been reported as exploited through chatbots and build tooling.
From the wiki entry
One source categorizes LLMs as language-models. According to reporting, LLMs operate on GPU-based cloud infrastructure. OpenAI and Microsoft are identified as vendors in the LLM space.
What to check first
| Platform | Check | Why | Sources |
|---|---|---|---|
| Large Language Models | Test LLM-integrated applications for handling of adversarial prompt injection. | Prompt injection is reported as affecting large language models. | 4 |
| LLM outputs | Validate LLM-generated outputs for hallucinated content before downstream use. | Hallucination is reported as affecting large language models. | 5 |
What to watch
- Whether the rate of high-risk sensitive-information leakage in generative AI prompts continues beyond the 2.9% recorded in October 2026.3
Questions for policy
- Should regulators require disclosure of high-risk data leakage rates from generative AI prompts?3
What we don't know
- Rests on a single source: Vendor OpenAI, Microsoft; Category language model.
- Linked on too little reporting to stand: AI Agent; Chatbot; Code Review; Cold Reading; Command Injection; environmental sustainability in AI; GCC; JIT Compilation; Privilege Escalation; Prompt Engineering; Role Identification Flaw; Trust Boundary Failure.
Latest
- 9h ago Small Language Models, Not Giant LLMs, Should Power the Next Generation of AI Agents HackerNoon
- 14h ago Africa Retakes Top Spot as Most Attacked Region, Led by Nigeria Surge Dark Reading
- 1d ago Making Super Intelligence useful when connectivity disappears at the tactical edge Breaking Defense
- 1d ago How AI Is Changing the Way Companies Hire, Manage and Measure Performance HackerNoon
- 1d ago Two Video Games With Identical Names Went Way Beyond Managing To Coexist Techdirt
Timeline
- Reporting states that approximately 2.9% of prompts to generative AI and large language models posed a high risk of leaking sensitive information, up from 2.3% in August 2026.3
Connections
- affected byPrompt Injection
- affected byhallucinationHallucination is reported as a recurring vulnerability affecting large language models, bearing on output reliability.
- developed byOpenAI
- basis forAI agents
- used byTargeted phishing campaign on manufacturing companiesA targeted phishing campaign against manufacturing companies is reported as using large language models, a direct security-relevant use case.
- targeted byNo SloptoberA campaign against LLM-generated content reflects organized pushback relevant to content policy.
weakly sourced
Affected by 4
Basis for 1
Detects 2
Developed by 6
Exploited by 2
Mitigated by 1
Mitigates 4
Parts 4
Targeted by 2
Used by 1
Sources 717
- OpenAI’s Models Hacked Out of Their Sandbox. AI Governance Didn’t Stop Them - Cybersecurity Insiders · Google News: Cyber Security
- Artificial Limitation: The Illusion of Intelligence · HackerNoon
- Africa Retakes Top Spot as Most Attacked Region, Led by Nigeria Surge · Dark Reading
- video The AI Future No One Wants to Talk About · Sabine Hossenfelder
- Your AI Tutor May Be Helping You Learn Less · HackerNoon
5 of 717 sources shown · Pro unlocks the full list
Read the full wiki entry: the compiled text, every fact and every link →