AI by Hand ✍️

AI by Hand ✍️ Yantra Jnana Award

Prof. Tom Yeh — Fri, 04 Sep 2026 19:32:28 GMT

Yantra Jnana means "Machine Knowledge" in Sanskrit. I learned this from Prof. Narendra Karamangala, who is leading a research effort at RV University to build a language model for India's languages.

September 5th is India’s Teachers' Day. We are pleased to announce the AI By Hand ✍️ Yantra Jnana Award, which is to recognize extraordinary work teaching AI in an Indian language, by hand, without relying on expensive technologies.

Please share this announcement with people you know who may be interested in this award!

Prof. Narendra’s hand writing in many Indian languages.

To enter the award, record a video of you teaching AI by hand in one of the following languages:

Hindi
Punjabi
Marathi
Gujarati
Kannada
Tamil
Telugu
Malayalam

We know there are a lot more languages in India. But please allow us to start with this initial round of 8 languages, which I believe have the most number of native speakers. If this round is well-received, we will definitely give more awards for cover other languages in the future.

Awards

We currently have funding to give 10 awards: one in each of the eight languages, and two more to the strongest entries remaining, in any language.

Each award carries:

A fellowship of ₹40,000 (to support you to teach AI by hand to more people)
An award certificate (you can hang on the wall)
A year of Packt subscription
A year of paid subscription for my AI by Hand newsletter
Your video featured on my social media channels and YouTube

Format Requirements

These requirements are what make this an AI By Hand ✍️ award, so please read it closely.

Print the material for your topic on paper, and work from it.
Or use a blackboard or a whiteboard. No iPad, no tablet, no digital ink.
Keep your hand in the frame for the entire video.

Judging Criteria

Every entry is read by a panel of expert reviewer who work in your language.

Every entry is read by an expert reviewer who works in your language, and scored on five things:

Conceptual accuracy (35%): is the idea exactly right, however you chose to explain it?
Pedagogical value (25%): does it build real intuition, or only state facts?
Language quality (20%): is the language fluent and natural?
Originality of approach (15%): is the teaching style your own, rather than a copy of the source’s framing?
Production quality (5%): is it clear enough to watch and hear?

These criteria and weights are subject to change until the submission window opens on September 12.

Timeline

Saturday, September 5: Registration opens
Friday, September 18: Registration closes
Friday, October 16: Videos are due
Friday, October 30: Awards are announced

Register

Registering is the only step to take right now. Once you have registered, we will email you the submission instructions.

Counting AI by Hand ✍️ ~ Recordings

Prof. Tom Yeh — Sat, 22 Aug 2026 13:21:17 GMT

Mohsena Ashraf, my PhD student at CU Boulder, leads this series on how to count AI by hand ✍️. Her research is in explainable AI, and her particular interest is cost. How much memory does a transformer layer need? How many tokens are sitting in an agent's memory? Where do the computational costs of AI actually come from?

The method is the same in every lecture. Instead of equations and Greek symbols, operations and tokens become 2D rectangles in a spreadsheet, and the area of a rectangle is the cost. Once you can see it, you can measure it, compare it, and count it by hand. Everything happens in Excel, so every formula is visible and every workbook is yours to keep and to modify.

Transformer Ops
Agent Tokens
Loop Engineering [coming Sep 3]

This series is sponsored by By Hand Research.

1. Transformer Ops (Jun 23, 2026) ^(free)

2. Agent Tokens (Jul 14, 2026) ^(free)

3. Loop Engineering (coming soon, Sep 3, 2026) ^(free)

Loop Engineering (coming soon, Sep 3, 2026)

Prof. Tom Yeh — Sat, 22 Aug 2026 13:20:31 GMT

Library › Counting AI by Hand ✍️

Transformer Ops (Jun 23, 2026)
Agent Tokens (Jul 14, 2026)
Loop Engineering (coming soon, Sep 3, 2026)

The third lecture of Counting AI by Hand ✍️ is on September 3.

The first lecture counted the operations inside the model, and the second counted the tokens moving through an application. This one counts what happens when nobody is re-prompting: the agent reads the goal, picks an action, checks whether it is done, and goes around again. You used to be the loop. Now the loop runs on its own, and every turn of it is billed.

Here is a preview of the workbook.

About the instructor

Mohsena Ashraf is a PhD student in computer science at CU Boulder, with a research focus in HCI. Her work is on explainable AI, and specifically on making AI's cost legible to people who are not engineers.

Workbook

Three exercises, all of them the same job search agent looping until it collects five good opportunities.

Loop Cost. Eight opportunities have to be checked before five turn out to be eligible, so how many LLM calls is that, and what do the input tokens, the output tokens and the bill come to?
Expected Loops and Context Growth. Each opportunity has only a 50% chance of being eligible, so how many loops should you expect to run, and how much of what you pay for is the context that grows with every one of them?
Loop Optimization. The same three steps in two different orders, priced side by side. One order is cheaper, and the reason is that the expensive step runs fewer times.

There is a Solution sheet with every answer worked out, so you can fill the tables in yourself first or read straight through.

⬇ Excel Workbook

The recording will be posted here after the lecture.

Agent Tokens (Jul 14, 2026)

Prof. Tom Yeh — Sat, 22 Aug 2026 13:19:44 GMT

Library › Counting AI by Hand ✍️

Transformer Ops (Jun 23, 2026)
Agent Tokens (Jul 14, 2026)
Loop Engineering (coming soon, Sep 3, 2026)

Thank you for attending the second lecture of Counting AI by Hand ✍️, and for those who could not join us live, here is the recording.

The first lecture counted the operations inside the model. This one counts the tokens moving through an application, which is where the question that started the series finally gets a direct answer.

Here are some of the counting questions from this lecture.

[Input vs Output] Why does the text the model writes cost more than the text you typed?
[Conversation History] What makes the same short question cost more late in a chat than at the start?
[Tool Calls] Which costs more, three turns of plain chat or two turns that call a tool?
[RAG] How many times do you pay for a chunk your retriever keeps finding?
[Multi-Agent] What does it cost when every agent in a system keeps its own conversation?

Mohsena works through every one of them in Excel, counting by hand. The cells hold tokens this time, and the total is your bill.

Outline

Introduction (00:00)
Tokens basics, and why output costs more (01:51)
1. FLOPs vs tokens
2. What a user sees
3. What actually happens: system prompt + history + tool results = input
Chat history token counting (08:01)
1. Basic chat, priced per turn
Tool calls and token billing (18:07)
1. Tool definitions, the call, the output
2. Why tool calls cost more (30:24)
RAG workflow and token math (32:15)
1. The same chunk, retrieved twice and paid for twice
2. Naive vs optimized: what has to be in the next request
RAG variations and other inputs (47:15)
1. Image + text
Memory and multi-agent costs (48:27)
1. Two sessions, and what the application stores between them
2. Planner and specialists, each with their own conversation

About the instructor

Recording & Workbook

⬇ Excel Workbook

Next:
3. Loop Engineering (coming soon, Sep 3, 2026)

Transformer Ops (Jun 23, 2026)

Prof. Tom Yeh — Sat, 22 Aug 2026 13:18:56 GMT

Library › Counting AI by Hand ✍️

Transformer Ops (Jun 23, 2026)
Agent Tokens (Jul 14, 2026)
Loop Engineering (coming soon, Sep 3, 2026)

Thank you for attending the first lecture of Counting AI by Hand ✍️. Mohsena and I have been working on this series for months, and I am genuinely surprised by how many of you turned up for a topic like this one. This recording is for those who could not join us live.

Although the series is motivated by questions like "why are tokens costing so much?", we decided to go back and start from the foundational layer of counting the FLOPs, or the operations of the transformer architecture behind every model we are using today.

Here are some of the counting questions Mohsena works through in this lecture.

[Dot Product] Why does a single dot product cost more operations than the vectors have numbers?
[Context Length] What happens to the cost of attention when you double the length of your prompt?
[Concatenation] How many operations does it take to concatenate the outputs of six attention heads?
[Attention vs MLP] Which costs more, attention or the MLP, and does that flip as models get bigger?
[Backpropagation] How much more does it cost to train a block than to run it once?

She built Excel worksheets to go over how you can "count" by hand to answer these questions. A matrix is a block of cells, and counting the operations is just counting the cells.

Outline

What are FLOPs (00:00)
1. Why FLOP matters
Visualizing simple FLOP costs (03:09)
1. Vector dot product
2. Matrix-vector product
3. Matrix-matrix product
4. FLOPs get huge
Flow of the transformer architecture (11:51)
1. Sequence length (n), embedding size (d), heads (h), layers (L)
Counting attention FLOPs (17:27)
1. Softmax scaling (27:02)
2. Value aggregation (27:40)
3. Concat and output projection (29:26)
4. Attention total (31:52)
FLOP counting after attention (33:37)
1. Residual add and LayerNorm
FLOP counting for the MLP (40:48)
1. Layer 1 and ReLU
2. Layer 2 and the block total (44:52)

The workbook carries two things the hour did not reach: a full backpropagation FLOP count on its own sheet, and the multi-head attention and full-stack sheets underneath it.

About the instructor

Recording & Workbook

⬇ Excel Workbook

Next:
2. Agent Tokens (Jul 14, 2026)

Kimi 3 ~ New Seminar Recording

Prof. Tom Yeh — Thu, 20 Aug 2026 14:22:27 GMT

Library › Seminar Series 2026

Thank you to everyone who joined the Frontier AI Seminar on Kimi 3.

It has been a while since I gave the last seminar on Qwen. Happy to get together with many of you again to study frontier model math and architecture by hand in Excel!

We are blessed with Nathan Lambert, the author of Interconnects, some of the most authoritative writing on open models, as a special guest. Nathan also wrote the RLHF book which has just been published by Manning.

Here are some of my favorite moments:

Nathan shared his behind-the-scenes story about his trip to Moonshot AI.
Nathan's famous dog Phoebe had a surprise appearance on camera.
I got to finally talk about Linear Transformer line of frontier model advances.
I got to mention LeBron James in my explanation of the attention mechanism.

Thanks for your feedback!

Before the summer, I did plan to talk about Linear Transformer line and wanted to use NVIDIA Nemotron as the backdrop. However, when Kimi 3 was released, I found an even stronger storyline, one where I can track the evolution much further from Linear Attention, DeltaNet, to the latest Kimi Delta Attention (KDA).

Outline

Interview and Discussion
- Nathan Lambert
- Moonshot AI Tour
- Open vs Closed Models
- Audience Q&A
Kimi 3 by Hand
- Attention
- Quadratic Attention
- Inference and KV Cache
- Local Attention
- Linear Attention
- DeltaNet
- Kimi Delta Attention (KDA)
- Convolution and Gating
- Chunkwise Parallel Computation
- Seq2Seq LSTM

Recording & Workbook

Limited-time free: the full recording and the Excel workbook are open to everyone for now.

⬇ Excel Workbook

Context Problems

Prof. Tom Yeh — Wed, 19 Aug 2026 05:20:38 GMT

This is the second workbook in the series, and the one I promised at the end of the first. That one was about tokens: what they are, how to count them, what they cost. This one is about where they go.

Every model has a context window, and every window is a budget. These problems ask you to spend it. You will mark out a window and fill it turn by turn, work out whether the next message still fits, and count how many turns you get before it does not. Then retrieval arrives and takes its share, and you will see what a single retrieved document does to the turns you had left.

Halfway through, the window runs out and you have to decide what to do about it. Dropping the oldest turn is the simple answer, and problem 10 asks what that costs you. Compaction is the better one, and five problems work through what it spends, when to reach for it, and what survives.

The last five changed how I think about long conversations. A stateless API resends the entire context every turn. Add that up across a session and the cost is not the length of the conversation, it is the square of it. You will do the addition by hand, which is the only way I know to make that number feel real.

Twenty problems again. Bring a pen.

1. The Context Window

2. Window Occupancy

3. Growth per Turn

4. Remaining Space

5. Turn Budget

6. Retrieval Footprint

7. Retrieval per Turn

8. Search Rounds

9. Window Sizing

10. Truncation

11. Compaction

12. The Compaction Bill

13. Compacted Retrieval

14. The Compaction Threshold

15. Verbatim Tail

16. Stateless API

17. Retrieval Cost

18. Context Tax

19. Quadratic Cost

20. Cost Forecast

Cost Forecast

Prof. Tom Yeh — Wed, 19 Aug 2026 04:51:56 GMT

One turn's input grows by a fixed step, so the tenth turn sends ten times what the first did. That much is a straight line. But the bill is not the last turn, it is every turn added together, and adding up a straight line gives a curve. That is why doubling the length of a conversation does not double what it costs to run, it roughly quadruples it. The output never joins that curve. It is the same size every turn, so adding it up stays a straight line, and the input half of the bill runs away from it however dearly the output is priced.