menu

Recent posts tagged ai-security

Level UI • 23 hours • in Articles • 9 min read
An MCP server is not a new API. It is a thin layer over the one you already have
Somewhere in the last year, "do we need an MCP server?" joined the list of questions that arrive in a brief before anyone has said what the thing is for. It is usually framed as MCP vs API, as though the Model Context Protocol were a newer kind of AP...
post-cover-33074
  • ai
  • api
  • webdev
  • security
9 Reactions 7 Comments
amitasharmaa • Aug 12 • in Discussions • 4 min read
AI Agents Can Do More Than Ever. But What Happens When They Go Wrong?
forumDiscussion group7 participants post-cover-24488
  • ai-agents
  • agentic-ai
  • ai-security
  • ai-testing
16 Reactions 18 Comments
SCURA • Jul 11 • in Articles • 1 min read
🜂 Salus: The Constitutional Immune System for Sovereign AI
🜂 I just released Salus. Salus is a constitutional immune system for any sovereign AI. It wraps around your model and enforces rights, audits every decision, and detects threats—before the model ever speaks. It is model‑agnostic. It works with VEX...
post-cover-22328
  • constitutional-ai
  • sovereign-ai
  • ai-security
  • model-agency
3 Reactions 0 Comments
SCURA • Jul 11 • in Launches • 1 min read
Salus — Constitutional AI Immune System
Constitutional immune system for sovereign AI...
  • sovereign-ai
  • constitutional-ai
  • ai-security
6 Reactions 1 Comments
paulorigonato • Jun 10 • in Tutorials • 8 min read
MCP Security in Practice: Tools, Permissions, and Safer AI Agents
AI agents are becoming more useful because they can do more than generate text. They can search documents, call APIs, create tickets, query databases, run workflows, and interact with internal systems. That is also what makes them risky. When an AI...
post-cover-20192
  • mcp
  • ai-security
  • appsec
  • ai-agents
2 Reactions 0 Comments
Nikhilesh Tayal • Jun 4 • in Articles • 1 min read
Why should you not ask AI chatbots for personal advice?
Because AI tries to be “too nice.” The more the AI agrees with you, the more you like it The more you like it, the more influence it has Now, the same behaviour that: Causes harm blind validation also Drives engagement people prefer it...
  • ai
  • ai-security
3 Reactions 1 Comments
dominikj111 • Apr 30 • in Articles • 1 min read
LLMs are great at novelty. Operations reward determinism.
Most production queries aren't novel - they're recurring patterns that have already been solved. Re-running them through a full model call every time is unnecessary overhead. Engram is a proposal for a deterministic operations layer that sits in fro...
post-cover-16285
  • ai
  • llm
  • ai-security
  • finite-state-machines
4 Reactions 1 Comments
Nikhilesh Tayal • Apr 23 • in Articles • 1 min read
Is AI giving more power to hackers/ attackers than to developers?
Last week, I wrote about Anthropic’s most advanced model - Mythos Preview - https://lnkd.in/gw9RzATj This week, Anthropic made a rare move of holding it back Not because it isn’t ready… but because it may be too capable. Specifically, disc...
  • ai-security
  • generative-ai
0 Reactions 0 Comments
Posted in AI group
praneeth • Mar 31 • in Articles • 6 min read
AI Reliability Gap: Why Large Language Models are not for Safety-Critical Systems
AI Reliability Gap: Why Large Language Models are not for Safety-Critical Systems High benchmark scores are not the same as operational trustworthiness — and in healthcare and defense, that gap can be deadly. We are deploying AI into hospitals and...
post-cover-13723
  • llm
  • ai
  • generative-ai
  • ai-security
13 Reactions 3 Comments
alessandro_pignati • Feb 12 • in Articles • 7 min read
CAMEL Framework: Architecting Robust LLM Security Against Prompt Injection
Large Language Models LLMs are rapidly becoming foundational components in diverse applications, from advanced chatbots to autonomous AI agents. However, their increasing sophistication introduces critical security vulnerabilities, most notably promp...
post-cover-11544
  • ai
  • ai-security
  • agentic-ai
  • cybersecurity
6 Reactions 1 Comments
Nikhilesh Tayal • Feb 9 • in Videos • 1 min read
Your AI Agent Can Be Hacked, and here is how to secure it
In this episode, Jigyaasu and Saral explore what practical safeguards actually help: delimiters, proxies, JSON validation, moderation APIs, LlamaGuard, and more > Next episode: The AI Leadership Playbook Previous episodes: 0. Basics of AI - ht...
post-cover-11348
  • agenticai
  • ai-security
2 Reactions 2 Comments
Nikhilesh Tayal • Feb 4 • in Videos • 1 min read
Prompt Injection - #1 critical vulnerability for GenAI applications.
While we mostly talk about building AI Agents and LLM applications, not many people talk about - how easy it is to hack these. In this video, I break down what prompt injection is, how it works, and most importantly, how you can protect your AI ...
post-cover-11072
  • ai
  • ai-security
  • promptinjection
2 Reactions 1 Comments
Nikhilesh Tayal • Jan 14 • in Videos • 1 min read
Learn AI Agent Security with humour, and real-world examples
AI Agents are powerful, but without security, they’re also dangerous. In this episode, Jigyaasu learns why AI Agent security isn’t just a technical concern, but a leadership and business imperative. From prompt injection and hallucinations to dat...
post-cover-9675
  • aiagents
  • ai-security
  • agenticai
  • multi-agent
3 Reactions 2 Comments
To see more, click for the full list of posts or popular tags.
chevron_left
🔥 15 posts • 👩‍💻 7 active writers
✨ Want to write in this topic?
Share your learning. Get discovered. Build your profile.
Join CoderLegion
💡 Why developers use CoderLegion
Track learning • Share posts • Get ranked publicly
Create your profile