AI tool comparison
DeepTutor vs How LLMs Work
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Education
DeepTutor
Agent-native learning assistant with five modes and persistent memory
75%
Panel ship
—
Community
Paid
Entry
DeepTutor is an agent-native personalized learning assistant from HKUDS (Hong Kong University Data Science Lab). Unlike most "AI tutor" products that are just chatbots with educational prompts, DeepTutor was architecturally designed from the ground up for multi-step learning sessions. It offers five integrated modes: Chat (conversation), Deep Solve (step-by-step problem solving), Quiz (adaptive assessment), Deep Research (literature-style investigation), and Math Animator (visual math explanations). Version 1.0.1 shipped April 10. The persistent cross-session memory is the technical differentiator. DeepTutor tracks what you've studied, what you've struggled with, and what you've mastered across sessions, using that context to adapt its approach. This is closer to how a human tutor operates — building a mental model of the student — than the stateless Q&A loop most AI tutors offer. DeepTutor supports OpenAI, Anthropic (Claude), and DeepSeek backends, making it backend-agnostic for institutions with existing API relationships. The Math Animator mode generates step-by-step visual breakdowns of mathematical problems, which addresses one of the weakest spots in current text-based LLM math tutoring. With 1,424 stars gained in a single day and 16.1k total stars, this is clearly meeting a real demand in the education space.
Education
How LLMs Work
Andrej Karpathy's LLM lecture, rebuilt as an interactive visual experience
75%
Panel ship
—
Community
Free
Entry
"How LLMs Work" is a free, browser-based interactive guide that walks through the complete pipeline for building large language models — from raw web scraping to RLHF-trained conversational assistant. Created by Yash Narwal and based on Andrej Karpathy's technical deep-dive lecture, it's been getting significant traction on Hacker News (214+ points) for turning dense ML theory into something genuinely accessible. The site covers data collection and deduplication, Byte Pair Encoding tokenization with a live demo, pre-training and next-token prediction, inference with a probability sampling simulator, post-training with RLHF, and RAG. Each section uses animated visualizations, clickable pipeline diagrams, and canvas-based graphics — not static explainer images. The progressive narrative structure follows a single piece of text through every stage of the pipeline, making abstract concepts concrete. In an era where everyone uses LLMs but few understand how they work, this kind of high-quality educational resource matters for a different reason than tools: it raises the baseline competency of the entire developer ecosystem. Better-informed builders ask better questions, make better design decisions, and push vendors toward more transparency. This is the kind of project the HN community rewards — and deserves the signal boost.
Reviewer scorecard
“Cross-session persistent memory is the missing piece in AI tutoring. Every other tool resets to zero each session. The five-mode architecture also makes sense — different learning tasks need different interaction patterns, not a one-size chatbot. Strong technical foundation from a credible academic lab.”
“Best visual explanation of tokenization I've seen — the live BPE demo finally made it click for me after years of reading static diagrams. Bookmarked for onboarding new engineers and explaining RAG to non-technical stakeholders.”
“Academic lab projects often look impressive on GitHub but stall after the paper is published. Support burden for open-source educational tools is brutal — student use patterns are unpredictable and error-prone. The Math Animator mode sounds great but math visualization AI is notoriously unreliable for complex topics.”
“It's a beautiful explainer, but Karpathy's own YouTube lectures already do this and go deeper. Building on someone else's lecture without significant original contribution is fine, but 'Ship or Skip' implies you'd use it now — this is more bookmark-and-forget.”
“Personalized education at scale is one of AI's most transformative applications. Cross-session memory is the first step toward a true AI tutor that knows your learning style, pace, and gaps. DeepTutor is early, but the architecture is the right one for where this is going.”
“The gap between AI capability and public understanding is the single biggest risk factor for good AI policy. Tools like this that translate technical reality into accessible visuals are infrastructure for an informed society — more important than most 'real' tools.”
“For self-learners trying to pick up complex topics — design systems, coding, statistics — a tutor that remembers where you left off and adapts the difficulty is a game-changer. The quiz and deep-solve modes in particular map well to how creative professionals actually want to learn new technical skills.”
“The scroll-based animation and progressive reveals are exactly how technical content should be designed. Whoever built this UX understands both pedagogy and web craft — it's a masterclass in making complex systems legible through thoughtful visual design.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.