Skip to content
All tags

#self-study

19 posts
ai guide

Should You Rent a GPU to Learn Model Training? GPUtw.ai, LoRA, Jupyter, and the First Experiment

GPUtw.ai makes sense as a short-rental GPU learning tool: start with Jupyter, Ollama, or ComfyUI, then try LoRA/QLoRA on a small model. It is not a large foundation-model training platform, and the first run should verify deployment, billing, and data retention with a small budget.

ai guide Reading CMU 07-280

Completing CMU 07-280: What You Know, What Is Missing, and What Comes Next

Finishing 07-280 means more than reading 24 guides: produce a search engine, supervised-model comparison, CNN/GPT-2 experiments, and a small RL-plus-MCTS system before choosing 07-380, 10-301, or a specialist course.

Linear Regression: From LMS to Locally Weighted Regression

Linear regression is more than a best-fit line: Chapter 1 connects squared loss to gradient descent, normal equations, maximum likelihood, and locally weighted regression.

Berkeley CS285 Homework and Final Projects: The CPU, GPU, and H100 Boundary

Five assignments move from CPU-friendly imitation learning to H100-based LLM RL and six-hour offline-RL runs; self-learners should use three compute tiers instead of copying the entire enrolled workflow.

Berkeley CS285 L1–4: Imitation Learning, Distribution Shift, and RL Basics

The first four lectures move from behavioral cloning to MDPs; HW1 turns distribution shift into an observable failure through MSE policies, DAgger, and flow matching.

Berkeley CS285 Spring 2026 Guide: 25 Lectures, Five Assignments, and the Self-Study Boundary

Spring 2026 CS185/285 publishes slides for 25 lectures, nine discussion units, five assignments, and starter code; current recordings require bCourses access, while HW4 defaults to an H100, so this is not a zero-cost open course.

Berkeley CS288 Spring 2026: 18 Slide Units, Three Assignments, and the Limits of Self-Study

CS288 moves from n-grams to RAG, reasoning, and agents through 18 public slide units and three assignments; Berkeley-only recordings make this an A3 materials route, not a public video course.

CMU 10-301/601 Spring 2026: Learn Machine Learning Through Nine Assignments

Spring 2026 publishes material for 27 lectures and nine homework bundles; outsiders can do the core work but cannot access Panopto, Piazza, Gradescope, or official homework solutions.

Stanford CS107 Lecture 1: From the Course Map to the Unix Command Line

Winter 2026 opens by explaining why CS107 goes below programming-language abstractions: from bytes and memory through assembly and heap allocators. It then lays out the 40/10/20/30 grading structure and closes with a first tour of the Unix command line.

Stanford CS229: Notes Rewritten Every Year, Public Problem Sets Frozen at 2020, and an Official Self-Test From 2008

The three things you need to self-study CS229 run on three different clocks. The lecture notes are 278 pages and were recompiled in August 2026. The newest problem sets you can download are from summer 2020. The self-assessment Stanford Online tells you to attempt before enrolling is a PDF created in 2008. Seventeen lectures from spring 2026 are public, and the last three are mislabeled.

Stanford CS336: The Lectures Are Runnable Python, and From Assignment 2 On You Pay for the GPUs

Of the seventeen regular CS336 lectures, only nine are executable Python programs; the other eight are PDF slide decks — and the split falls exactly along the two instructors. Assignment 1's handout carries eight 'Low-Resource Tips' for finishing it on a laptop. Assignments 2 through 5 carry none. The course page lists the hourly price of a B200; the handouts list how many B200 hours each problem needs.

learning deep-dive

CMU's AI Degrees: The First U.S. AI Bachelor's Turned 'What Should AI Students Learn?' into Graduation Requirements

Stanford has no AI degree; AI is a track inside CS. CMU launched the first U.S. B.S. in Artificial Intelligence in 2018, divided AI into four clusters, required one course from each, and made ethics a graduation requirement. At the master's level, MSAII sits not in CS but in the Language Technologies Institute; 84 of its 195 units cover an innovation process ending in a fundable capstone. Two official-page conflicts emerged during verification: whether the AI Core has two or three courses, and whether MSAII totals 192 or 195 units.

A Global Map of AI and CS Courses: Which Ones Can You Actually Study in Public?

This map audits AI and CS courses at Stanford, CMU, MIT, and UC Berkeley in 2025–2026 using four access labels: A0 for a visible catalog entry, A1 for a public syllabus, A2 for partial materials, and A3 for a self-study-ready package. A course site or YouTube playlist can exist without giving outsiders access to the current videos, assignments, or starter code.

Stanford CS103: A Math Course Whose First Assignment Is Installing a C++ Compiler

CS103 teaches you how to write proofs, then teaches you what can't be proven — but the part nobody mentions is that it ships C++ programming assignments, starting with PS0: install Qt Creator. Its real asset is a shelf of homegrown 'Guide to X' handouts and a Proofwriting Checklist that graders actually deduct points against, all public. Solutions and practice exams sit behind Stanford login, and the Honor Code page explains why.

Stanford CS107: The Same Course Weights Assignments at 40% One Quarter and 20% the Next

CS107 runs from Unix and C all the way to x86-64 and writing your own malloc, across seven assignments. But line up four archived syllabi and the course stops looking like one course: assignments are worth 40% in three quarters and 20% in Summer 2026, where in-class quizzes take 40%. The resubmission policy exists only in the quarters Cain taught; Troccoli's quarter has none. The one assignment that accepts no late days is the final heap allocator. And what blocks a self-learner isn't the autograder — it's that every starter repo lives on AFS.

Stanford CS109: A Probability Course That Turned "How to Read This Lecture With an LLM" Into Official Coursework

Every lecture in CS109's Summer 2026 offering ships with an official LLM Learning Guide — six concepts, a Learn prompt and a Test me prompt for each, written week by week across the quarter for a total of 23 PDFs. The same course's honor code Rule 4 forbids asking an LLM to solve your homework, and 65% of the grade sits in proctored exam rooms. Those two facts are halves of one design.

Stanford CS111: Nine Assignments Build an Operating System, and the Exams Don't Test Them

CS111's nine assignments run from lambdas to crash recovery in a journaling file system. Reading the site page by page turns up three things the syllabus blurb never mentions: assignment 3 is the point of no return, because assignment 4 compiles your assignment 3 code; a whole block of the final exam asks for definitions of ethics terms, and the public practice sheet ships with answers; and pasting your own code into an AI tool to ask about it is written down, in plain words, as an Honor Code violation.

Stanford CS161: The Algorithms Course That Lists Writing Clearly as Its Third Learning Goal

The first slide of CS161 names three goals: design, analysis, communication. The third one is why handwritten homework scores zero and why solutions have to read like a memo to a colleague. Of the eight problem sets, HW2 is the wall. The lecture notebooks exist to show that timing runs can't tell you which algorithm is faster. And the summer offering is a completely different course wearing the same number.

A Reading Guide to Stanford's CS Courses: Ordered by Prerequisites, from CS106A to CS336

Stanford CS rests on CS103, CS107, CS109, CS111, and CS161; CS221 names three of those plus CS106B as preparation. This guide combines official prerequisites with an explicitly editorial reading order and marks public-material and offering risks.