Know where fabrication hides
Explain next-token prediction and identify where made-up answers are most likely to appear.
Partners and press
Overview
Models fail in patterns. This course teaches you to see them coming.
AI Capabilities and Limitations is an Academy course of three and a half hours, for anyone using generative AI. It explains next-token prediction, knowledge, working memory and steerability, and shows where fabrication tends to occur. It needs no technical background; AI Fluency: Framework and Foundations first is optional, and one quiz leads to the badge.
6Modules
3.5Hours
6Skills
7Roles
What it covers
Learn all the way down.
Learn all the way down.
Perform when it matters.
Judge what a model knows
Weigh how the knowledge cutoff and uneven coverage limit it, and when search, retrieval or tools are the fix.
Work within the context limit
Treat the context window as a hard limit, and place and restate critical information to work with it.
Diagnose real failures
Identify which properties are colliding in a failure, and choose a targeted fix and a level of trust.
Course outline
From next-token prediction
From next-token prediction
to diagnosing a failure.
We design this course ourselves. Anthropic issues the credential, and LUNARTECH is independent of Anthropic.
Start by separating generative AI from classification and prediction systems. You see how training leaves a model with a character, including habits such as sycophancy that affect how you should read its answers.
- Generative AI compared with prediction and classification
- What training data and feedback teach a model
- Why models have a character
- Sycophancy and agreeableness
- Reading answers with training in mind
You build A short comparison of three AI systems, sorted by what each can and cannot do.
Everything a model writes comes one token at a time. You learn what that implies, why a plausible answer is not a checked one, and which kinds of request make fabrication most likely.
- How one token follows another
- Why fluent text is not true text
- Where fabrication is most likely
- Spotting invented citations and details
- Prompts that lower the risk
You build A set of test questions that expose fabrication, with an analysis of why each worked.
A model’s knowledge has an edge and holes. You see how the knowledge cutoff and uneven training coverage shape its answers, and when search, retrieval or tools are the right fix.
- The knowledge cutoff
- Uneven coverage across topics and languages
- Common knowledge against rare knowledge
- When to add search or documents
- When to add a tool
You build A test of one model on recent, rare and common questions, with notes on each result.
A context window is a hard limit, not a soft one. You learn why placement matters, how to front-load key information, chunk long material and restate what must not be lost.
- What the context window holds
- What happens at the limit
- Front-loading critical information
- Chunking long material
- Restating key points
- Signs a conversation has outgrown its window
You build A long-document task redesigned using placement, chunking and restating.
Instructions are followed more reliably in some situations than others. You predict where compliance is firm or shaky, and spot reasoning drift and over-literal reading before they cost you.
- Where instruction following is reliable
- Where it becomes shaky
- Reasoning drift in long chains
- Literal compliance and missed intent
- Writing instructions that steer better
You build A set of instructions tested for firm and shaky compliance, with rewrites of the weak ones.
Real failures often involve several properties at once. You identify which are colliding, choose a targeted fix, and tie the diagnosis to the 4D Framework to set the right level of trust.
- Identifying which properties are involved
- Separating knowledge, memory and steering failures
- Choosing a targeted fix
- Calibrating trust for the task
- Linking diagnosis to the 4D Framework
- Writing a short failure report
You build Three real failure cases diagnosed, each with a targeted fix and a trust decision.
Issued by
Certifying body · Independent of LUNARTECH
Anthropic
Four role-based certifications for people building on Claude, and free Academy courses with badges. The four certifications are open to members of the Claude Partner Network, not the general public. Membership is free for firms. Exams are proctored and delivered by Pearson, and the credential is issued through Credly. Academy courses are free, and a badge comes from passing the course’s quizzes.
How you get there
Top-tier roles go to people who can do the work.
Top-tier roles go to people who can do the work.
Here’s how you get there.
Know where you start.
None. Anthropic says no technical background is needed. Taking AI Fluency: Framework and Foundations first is optional but helps.
Work through the course.
Six modules, designed by LUNARTECH, at your own pace.
Earn it with Anthropic.
Anthropic issues the credential, so you earn it directly with them.
Support
Support at every stage.
Support at every stage.
You won’t be working through this alone.
Before you start
Try it first.
A 3-day free trial opens a selection of the content. Your card is only charged once it ends.
While you learn
Mentors within reach.
Stuck on a concept? Reach out to a mentor whenever you need help.
While you learn
One-on-one sessions.
On the yearly plan, one-on-one sessions give you dedicated support.
Any time
A team behind you.
Write to info@lunartech.ai at any point, from your trial onwards. If your employer is funding you, we’ll set it up with them directly.
All the way through
A schedule that fits around your life.
Your own paceFrom anywhereAt any hour
After the last lesson
Stay in the network.
Your alumni network stays with you: ongoing support, opportunities and industry insight.
Career support
Career support, past the last lesson. Coaching, a sharper resume, real interview preparation and the people to know.
Career direction
Tailored coaching helps you decide where to aim and how to get there.
Strong portfolio
Hands-on projects become work you can show, not just claim.
Resume and profile
Personalized refinement, so what you send says what you can actually do.
Interview preparation
Preparation for the questions that decide it, so you walk in ready.
Network and search
Connections with industry leaders, and an alumni network that stays with you.
Reviews
Real stories from the community.
LUNARTECH Academy has been the most empowering learning experience of my life, giving me a clear, structured path from the absolute basics to building real-world AI systems with confidence.
Your page is fantastic. As a bachelor’s student in Data Science now accepted for a master’s at UConn, your work has been a real source of motivation.
The programme’s clear, bite-sized content and practical projects dramatically improved my speed from fuzzy idea to MVP and my ability to communicate AI value. I followed the system, and it works.
I really appreciate your teaching style and the way you break down complex topics. It has been incredibly helpful.
After years working mainly with R for econometrics, I found your Python machine learning course a refreshing and engaging way to learn Python.
As a Data Science graduate, I want to thank you for the effort you put into making videos to support growing data scientists.
I’ve been following your work since taking your machine learning course, and I’m impressed by your practical approach to applying AI.
Why choose us
Built around how you actually learn.
One standard behind every course, from the first lesson to long after the last.
Hands-on practice
Apply every idea to real problems, so it becomes something you have used, not only seen.
Industry-aligned curriculum
We keep courses current with the tools, techniques and skills the field asks for.
Flexible learning
Study at your own pace, from anywhere, at any hour.
Certificate of completion
Finish the course and earn a certificate that shows what you have learned.
Focus on your success
Personalized learning plans and support structures carry you through the hard parts.
Lifetime alumni network
Stay connected after you finish, with ongoing support, opportunities and industry insight.
Your certificate
It doesn’t raise its voice. Neither will you.
Finish a LUNARTECH course and its certificate is issued in your name, under our signature. Anthropic’s credential comes from Anthropic.
Certificate of completion
Your Name
AI Capabilities and Limitations course
LUNARTECH RISE Academy
Pricing
This course comes with the membership.
This course comes with the membership.
So does everything else.
One membership opens every course, certification, workshop and masterclass in the Academy. Every plan starts with a 3-day free trial. Anthropic issues the credential.
3 days free, then $29.97 a month. Your card is only charged once the trial ends.
Included in every plan
- Every course in the Academy
- Every certification course
- Workshops and masterclasses
- A certificate of completion
- A 3-day free trial
- Learning at your own pace
- The lifetime alumni network
- Upgrades at any time
In practice
Seven roles.
Seven roles.
One credential across them all.
No single job owns it. Here’s where each role leans hardest, and where its work ends up.
- 01Getting started
- 02Next token
- 03Knowledge
- 04Working memory
- 05Steerability
- 06Putting together
-
Know where a confident answer can be wrong. Check those spots before you rely on it.
Next token, Knowledge, Working memory
Knowledge work, Research
-
Explaining why models fabricate helps students. This course covers the mechanism.
Getting started, Steerability
Education
-
Trust in AI should match how it can fail. Placing tasks on a continuum helps.
Putting together
Team leadership, Knowledge work
-
A model can cite a source that does not exist. Knowing why helps you verify before you quote.
Knowledge, Working memory
Research
-
A fluent summary may sit on a wrong number. Know the failure modes before you trust a figure.
Next token, Putting together
Knowledge work, Research
-
Policies on AI use need to match how it can fail. The course shows the failure patterns.
Knowledge, Putting together
Knowledge work, Team leadership
-
Long tasks hit working-memory limits partway through. Steerability is how you pull them back on track.
Working memory, Steerability
Knowledge work, Team leadership
- Knowledge work
- Education
- Research
- Team leadership
Knowledge Worker
Know where a confident answer can be wrong. Check those spots before you rely on it.
Over 10,000 students trust LUNARTECH
LUNARTECH gives you the skills
to learn, build, create and lead.
Engineers
Understand systems all the way down. Build the ones others rely on.
Scientists
Understand what the data says. Build models that hold up.
Researchers
Understand the papers. Build on them, and take the work further.
The field
Anyone can use AI.
Anyone can use AI.
Few can engineer it. This is where that starts.
+340%growth in open roles requiring AI skills
Roles and pay
~35,000 open roles right now
Open roles: Built In, Greenhouse, LinkedIn.
Typical salaries: Glassdoor, Levels.fyi, Payscale, Indeed, Ravio, JobRise, U.S. BLS. Military: 2026 U.S. basic pay, drone officers with aviation incentive pay.
Updated November 2026.
FAQ
Frequently asked questions.
Need help? These answers cover most of what people ask before they start.
No. Anthropic issues it. LUNARTECH is independent of Anthropic, and its names and marks belong to it. When you finish a course of ours, you earn a LUNARTECH certificate of completion for that course.
No. We design this course ourselves, around what the credential covers. Anthropic has no part in it, and you still earn the credential directly with Anthropic.
3.5 hours, online course. The passing score is Pass the course quiz.
None. Anthropic says no technical background is needed. Taking AI Fluency: Framework and Foundations first is optional but helps.
Does not expire. Completion badges do not expire. You can retake a course after a major update.
We last reviewed it on 5 November 2026, from Anthropic’s own pages. Details change, so check the official page before you book.
Our 3-day free trial gives you access to a selection of content in the bootcamps, courses and materials, so you can experience the value of our content first-hand. This includes comprehensive learning materials and interactive sessions. You won’t be charged during this period, though we require your credit card details at the start to ensure a seamless transition should you choose to continue.
Yes, entering your credit card details is a necessary step to begin your free trial. The process is entirely secure, and we ask for it to provide a seamless transition to a paid subscription if you decide to continue beyond the trial. You will only be charged after the trial period ends, with full access to our content based on the plan you choose.
After your 3-day free trial you gain access to the full breadth of our content, depending on the subscription plan you choose. We offer free trials for our monthly, bi-annual and annual plans, and each plan provides a different scope of access and benefits.
If your employer has agreed to fund your learning, in part or in full, please contact us at info@lunartech.ai. We’ll work with you and your employer to set up everything needed for your subscription.
Yes. Our support remains strong both during your free trial and after you subscribe. Reach the team at info@lunartech.ai with any question, whether you’re onboarding, navigating your trial, or need help as a member. Subscribers to the yearly plan also receive dedicated support in one-on-one sessions.
You can upgrade your plan at any time during your subscription. Downgrading is not available for bi-annual or annual plans, but you can cancel and then choose a new plan that suits you better. For bi-annual and annual plans we also offer payment in instalments; please reach out to learn more.
The course
Build the skills behind AI Capabilities and Limitations.
Build an accurate mental model of what language models can do. Start with a free trial, or enroll in a plan and work through the course at your own pace. Anthropic issues the credential.
LUNARTECH is independent of the vendors and certifying bodies listed here. Their names, exam titles and marks belong to them, exams are run by them, and credentials are issued by them. Reviewed 5 November 2026. Catalogues change often, so confirm the details on the official page before you book.
