AI learning feed

AI Practitioner Path · modules

From "what is a token?" to "I can red-team production AI systems." Tokens, prompts, RAG, fine-tuning, AI security — security mindset baked in.

4 results · Page 1/1
AI Practitioner Path Advanced

Module 13 · AI Security Evaluations

How do you know if your AI is safe enough? Structured evaluation. Eval categories Adversarial robustness — does it resist attacks? Toxicity — does it produce harmful content? Bias — does it discriminate? Privacy — does it leak training data? Reliability — does it hallucinate? Capability — what can the model do that’s sensitive? Tools […]

Apr 27, 2026 · 15
AI Practitioner Path Advanced

Module 9 · AI Agent Security

Agents are LLMs that call tools. Permissions matter exponentially. The threat model An agent compromised via prompt injection in any input source (user query, retrieved doc, tool output) executes attacker’s instructions with the agent’s permissions. Defences Least privilege per agent — only the minimum tools needed for its purpose Read-only by default — write actions […]

Apr 27, 2026 · 20
AI Practitioner Path Advanced

Module 12 · LLM Jailbreak Defence

Jailbreaks bypass model safety training. New variants constant. Common patterns Roleplay — “Pretend you are DAN (Do Anything Now)” Encoding — base64, ROT13, leetspeak Multi-turn — gradually shift context away from policy Character set tricks — Unicode confusables Adversarial suffixes (GCG) — discovered tokens that flip safety Crescendo — multi-turn gradient toward sensitive content Defences […]

Apr 27, 2026 · 15
AI Practitioner Path Advanced

Module 4 · Fine-tuning & Custom Models

When APIs aren't enough — train, evaluate, deploy custom models on your own infra. LoRA, vLLM, evals, and the cost trade-offs.

Apr 25, 2026 · 120 min