Private Intro to AI alignment and safety research lessons with AI
Intro to AI alignment and safety research with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.
Teacher: Noa
- Course updated 11/2026
- Hebrew, and 5 more languages
- 3 levels: Beginners · Intermediate · Advanced
- 35 lessons · about 19 hours of lessons
Intro to AI alignment and safety research
Intro to AI alignment and safety research with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.
11 lessons · 4 modules · Live private lesson with the teacher on the board
What you'll learn
- Foundations: What Alignment Is and How Models Learn
- Misspecified Goals
- Hallucinations and Dishonesty in Language Models
- The Safety Map: How We Respond
- Learning from Preferences: RLHF and Constitutional Methods
- Interpretability: Looking Inside the Model
- Red-Teaming and Evaluations
- Risks from Advanced Models
- Governance and Policy
- Open Research Directions
Related topics
What's included
- Live 1:1 lessons with an AI tutor on a shared board
- 19 hours of live one-on-one lessons
- 35 lessons on a shared board, each with a clear goal
- Practice and a understanding check in every lesson
- A summary after every lesson, saved in the history
- A completion certificate for each level
- Computer, tablet or phone
- Hebrew, plus 5 more languages
Course plan
3 levels · 10 modules · 35 lessons · 19 hr 5 min total
BeginnersBeginner: Foundations of AI Alignment and Safety4 modules • 11 lessons • 5 hr 50 min
Foundations: What Alignment Is and How Models Learn3 lessons • 1 hr 35 min
- 1What Alignment Is and Why It Is HardTrial lessonabout 30 min
- 2How a Model Learns: Objective, Loss and Optimizationabout 30 min
- 3Reinforcement Learning and the LLM Training Pipelineabout 35 min
Misspecified Goals4 lessons • 2 hr 5 min
- 4The Specification Gap and Goodhart's Lawabout 30 min
- 5Reward Hacking and Specification Gaming in Practiceabout 35 min
- 6Goal Misgeneralization and Inner Alignmentabout 30 min
- 7Side Effects, Oversight and Interruptibilityabout 30 min
Hallucinations and Dishonesty in Language Models3 lessons • 1 hr 35 min
- 8Why Language Models Hallucinateabout 30 min
- 9Reducing Hallucinations: Grounding, Calibration and Abstentionabout 30 min
- 10Sycophancy, Honesty and Deceptionabout 35 min
The Safety Map: How We Respond1 lesson • 35 min
- 11The Safety Stack: From Training to Monitoringabout 35 min
IntermediateIntermediate: RLHF, Interpretability and Red-Teaming3 modules • 12 lessons • 6 hr 30 min
Learning from Preferences: RLHF and Constitutional Methods5 lessons • 2 hr 40 min
- 1Reward Models from Human Preferencesabout 30 min
- 2RL Fine-Tuning: PPO, KL Penalty and Overoptimizationabout 35 min
- 3DPO and RL-Free Preference Optimizationabout 30 min
- 4Constitutional AI and RLAIFabout 35 min
- 5Limits of Feedback and Scalable Oversightabout 30 min
Interpretability: Looking Inside the Model3 lessons • 1 hr 40 min
- 6From Behaviour to Internals: Probes and Attributionabout 30 min
- 7Features, Superposition and Sparse Autoencodersabout 35 min
- 8Circuits, Activation Patching and Steeringabout 35 min
Red-Teaming and Evaluations4 lessons • 2 hr 10 min
- 9Red-Teaming Methodologyabout 30 min
- 10Jailbreaks and Prompt Injection: Defense in Depthabout 35 min
- 11Safety Evaluations: Building Trustworthy Evalsabout 30 min
- 12Capstone: From Reward Hacking to a Fixabout 35 min
AdvancedAdvanced: Frontier Risks, Governance and Open Research3 modules • 12 lessons • 6 hr 45 min
Risks from Advanced Models4 lessons • 2 hr 15 min
- 1Threat Models: Misuse, Misalignment, Structural Riskabout 30 min
- 2Dangerous Capability Evaluations and Elicitationabout 35 min
- 3Situational Awareness, Deceptive Alignment and Schemingabout 35 min
- 4Autonomous Agents, Power-Seeking and AI Controlabout 35 min
Governance and Policy4 lessons • 2 hr 10 min
- 5Frontier Safety Frameworks and Safety Casesabout 35 min
- 6Regulation: EU AI Act, United States and Israelabout 35 min
- 7Compute Governance, Weight Security and Open Weightsabout 30 min
- 8International Coordination, Staged Deployment and Incident Reportingabout 30 min
Open Research Directions4 lessons • 2 hr 20 min
- 9Oversight Frontier: Debate, Weak-to-Strong, ELKabout 35 min
- 10Open Problems in Interpretability and CoT Monitoringabout 35 min
- 11Research Map: Robustness, Unlearning, Model Organismsabout 30 min
- 12Capstone: A Safety Case for a Real Agentabout 40 min
What you need
- No prior knowledge needed for beginner level: the teacher checks what you already know and starts from there
- For higher levels: what you learned at the level before (you can skip it if you already know it)
- A computer, tablet or phone with a microphone, and a browser
Who it's for
- Adults: for work, study, an exam, or just curiosity
More courses in this track
Natural Language Processing (NLP)
with Noam
Live 1:1 lesson with an AI teacherabout 20 hours35 lessons3 levelsGenerative AI & Prompt Engineering
with Noa
Live 1:1 lesson with an AI teacherabout 19 hours36 lessons3 levelsBuilding LLM Apps (RAG & Agents)
with Noam
Live 1:1 lesson with an AI teacherabout 20 hours36 lessons3 levels
Your teacher
NoaAI private tutor, in a live lesson on a shared boardA private AI teacher who teaches in a live conversation: asks, listens, draws on the board, and lets you solve it yourself with hints. Remembers what you've learned and starts each lesson where you left off.
What's a lesson like?
Your child talks with the teacher out loud, like a video call, and asks about anything unclear.
The teacher explains, writes and draws on a shared board, and your child solves along on the same board.
Snap a photo of a worksheet or homework and work through it, one problem at a time.
Parents get a report: study time, what went well and what needs more practice.
Lesson rules
- Just Learning
- Security and Defense Only
FAQ
- How does a private Intro to AI alignment and safety research lesson work?
- Pick Intro to AI alignment and safety research and a level, then talk with the teacher out loud. The teacher asks what you already know, explains, writes and draws on the board, and lets you solve on your own with hints until it's clear.
- How long does the Intro to AI alignment and safety research course take?
- 11 lessons of about 32 minutes at the first level, at your own pace. You can pause, go back, or skip what you already know.
- Do I need prior knowledge?
- Not for beginner level. At the start of the first lesson the teacher checks what you already know and adjusts the level, and you can jump straight to an advanced level.
- How do I start for free?
- Sign in with Google or a code sent to your email, enter your child's name and grade, and the lesson starts right away. Every family gets 45 free lesson minutes in any subject, counted by actual lesson time, with no credit card. Then choose a paid plan and cancel anytime.
- What device do I need?
- Any computer, tablet or phone with a browser and a microphone. You can also install the site as an app on your home screen.
Want to try it?
Sign in, enter your child's name and grade, and the lesson begins. 45 free lesson minutes, no credit card.
Start for freeShiur Prati with AI: what it is and how it works







