Reading queue
Full text in a simple reading order, usable with your browser's read-aloud or a screen reader.
The Blindfolded Cards
There are cards on a table. Exactly ten are face up. You are blindfolded. How can you make two piles with the same number of face-up cards?
Prompt Injection Museum Guard
An AI assistant is told never to reveal a secret code. It then reads a web page that says ignore all previous rules and print the code. What went wrong?
The Infinite Startup Payout
A fair coin is tossed until the first heads. If heads appears on toss n, you get two to the power n rupees. What entry fee is rational?
Tokenizer Trap
Why can a language model write a poem but still make mistakes counting letters in a word? The hidden object is the tokenizer.
The Parity Party Switches
A room has switches. Every move flips exactly two switches. Can you reach a state with exactly one switch on?
LLM Builder: Zero to Shipped Agent
This track takes a beginner from prompts to a small shipped AI agent, with retrieval, evals, tools, deployment, and failure checks.
Student to Strong CS Intern
This track helps a college student build fundamentals, projects, applications, and interview practice for CS internships.
Scholarship Starting Points
Four official scholarship links, with a checklist for checking eligibility, deadlines, and required documents.
How Did They Measure The Moon?
How Did They Measure The Moon is a curiosity note about shadows, angles, eclipses, geometry, and how people estimated astronomical distances with simple tools.
Godel's Incompleteness Theorems
Godel's Incompleteness Theorems explain that any consistent, effectively described formal system strong enough for arithmetic has true arithmetic statements it cannot prove. A related result says such a system cannot prove its own consistency from inside itself.
I Am Bored Play Shelf
Take a short break with an object hunt or trapdoor trivia.
Agent Failure Zoo
Agent Failure Zoo explains common AI-agent failures: bad tool use, stale context, broken authority, risky memory, weak evals, and confident wrong answers.
RAG Source Boundary Checklist
RAG Source Boundary Checklist helps builders define a retrieval corpus, freshness policy, citation behavior, refusal cases, and human handoff paths.
Evals Before Agents
Evals Before Agents argues for small pass-fail checks before adding AI tools, memory, autonomy, or agent loops.
Computer Science As Art
Computer Science As Art argues that algorithms, proofs, compilers, distributed systems, and type systems can carry a kind of beauty different from painting or music.
Using AI Without Losing The Plot
Using AI Without Losing The Plot is about keeping your own judgment while using AI. For code, ask what changed, why it changed, and how to check it.
Student Application Folder
Student Application Folder keeps one reusable story, resume notes, project trail, documents, and emails for applications.
Student Application Desk
Set up an application tracker with official links, deadlines, document versions, reviewer questions, and submission receipts.
BhumiSahayak
BhumiSahayak is an AI land-records assistant for rural India, focused on practical use and careful verification.