Retrieval
Your answer comes first.
Answer a focused question before reading the explanation. Use what you missed to decide what to practice next.
Recall it coldOne nudgeExplain the gap
The space between knowing & understanding
Understand the ML you work with.
Choose an ML or software engineering concept. Work through the intuition, math, and code with a tutor you can interrupt. Ask follow-up questions, then try explaining or implementing it yourself.
2 free sessions, no account needed.
2full sessions$0no account157indexed topics
A working simulation. Try the control.Study a concept
Classical MLDeep LearningReinforcement LearningTraining EngineeringSystems and MLOpsFrontendBackendSystem DesignUI/UXCS FundamentalsClassical MLDeep LearningReinforcement LearningTraining EngineeringSystems and MLOpsFrontendBackendSystem DesignUI/UXCS Fundamentals
Built for durable recall
A record of what holds up.
A chat remembers the thread. LiminalML remembers what you could retrieve, which implementation checks passed, and what is likely to fade next.
Implementation
def attention(q, k, v, mask):
scores = q @ k.transpose(-2, -1)
scores /= q.size(-1) ** 0.5
scores.masked_fill_(~mask, -inf)
return scores.softmax(-1) @ v test passes / gradients finite
Retention
Come back when recall is at risk.
The queue uses weakness, elapsed time, and prerequisites to choose a small number of worthwhile reviews.
Attention / mathdue today
Position / intuitionholding
Evidence
Not one vague mastery score.
Keep separate evidence for intuition, math, implementation, systems decisions, failure modes, hints, and tests.
evidence record
Systems: strong · Math: due · Implementation: 6/6 checks · Hint use: none
The six-stage loopOrient
Orient
See the whole idea before the machinery.
Start with the problem, the constraints, and the mental model that makes every later equation feel inevitable.
Leaves you with a durable mental model.
The real interface
Don't take the landing page's word for it.
Try an example study session. Follow the math, inspect the code, and ask a follow-up before moving on. No account needed.
Attention, from intuition to implementation.
An example session with math, code, and follow-up questions.
Open technical references
17 deep dives for when the gap really is knowledge.
Deep LearningAttention MechanismsHow scaled dot-product and multi-head attention work; the soft key-value lookup at the heart of every Transformer; with the math, runnable PyTorch, and calibrated interview questions.9 min · deep diveDeep LearningTransformer ArchitectureThe Transformer block from the ground up; self-attention plus a position-wise feed-forward network, residuals and LayerNorm, and the encoder/decoder configurations; with the math, PyTorch, and calibrated interview questions.9 min · deep diveDeep LearningBackpropagationBackpropagation as reverse-mode autodiff; the chain rule over the computational graph, the gradients for a linear layer and ReLU, and why gradients vanish; with a runnable manual backward pass.9 min · deep diveDeep LearningBatch NormalizationWhat Batch Norm normalizes and why, the critical train-vs-inference distinction, BN vs. Layer Norm, with the math and a from-scratch PyTorch implementation.8 min · deep diveOptimizationGradient Descent (SGD, Momentum, Adam)SGD, momentum, and Adam explained; the update rules, why mini-batching wins, Adam's bias correction, and when plain SGD generalizes better; with from-scratch implementations.8 min · deep diveLLMsKV CacheHow the KV cache makes autoregressive LLM decoding affordable; what it stores and why reuse is valid, the memory cost, why decoding is memory-bandwidth-bound, and how MQA/GQA shrink it; with code.8 min · deep dive
Two tracks, one method
Choose the depth. Keep the structure.
Interview prep is the sharpest use case, but the product is built for any engineer who wants a concept to survive beyond the tab they learned it in.
ML / Research71 topics
From classical models to training systems.
Transformers, optimization, RLHF, distributed training, serving, and the mathematics underneath modern systems.
Software engineering86 topics
From browser internals to distributed systems.
Rendering, caching, databases, data structures, backend architecture, and production tradeoffs.
Pricing
Try it before you exist to us.
Only Pro takes a card. The trial does not charge for seven days and cancels in one click.
Guestno account
$0
2 full sessions, then sign in
Two complete six-stage sessions
All 157 topics and 17 deep technical references
No email, no card, no profile
No practice lab, nothing saved between visits
Freesign in
$0
8 sessions a month
8 sessions a month, no card
Saved threads you can resume
Mastery evidence and an adaptive review queue
12 retrieval evaluations a month
5 practice-lab code reviews a month
Revision cards
Stage 6 grounded in your resume, not generic examples
Pro7-day trial
$9 / month
Unlimited sessions
Unlimited review sessions
Unlimited practice-lab code reviews
Unlimited retrieval evaluations and mastery history
Everything in Free
New topics ship to Pro first
Request topics directly
Start before you sign up
Pick the concept you keep almost understanding.
Work through the details, ask the follow-up, and test what stayed with you.
Start a deep study session2 sessions without an account · 8 / month when you sign in · unlimited on Pro