Book Cube
Books, ideas and engineering culture — every week
A Telegram channel with original notes and reviews on books about technology, architecture, management, economics and personal growth. Long-form posts with practical takeaways, no fluff, no ads.
Book Cube posts
Bilingual versions of channel posts, with sources and a link to the original Telegram publication.
- #AI4SDLC
Ollama: How Agents Are Changing Open-Model Economics (#AI4SDLC)
A breakdown of YC Lightcone's conversation with Jeff Morgan: agent-driven token growth, model portfolios, and Ollama's emerging role as an integration layer between local and cloud inference.
- #AI
AI for Mid-Sized Businesses: Episode Materials (#AI)
Materials from Code of Leadership episode 75 with Alexander Vorontsov on practical AI adoption in mid-sized businesses: the recording, written recap, and audio editions.
- #AI
Stanford MS&E435: Chai and Claude - Who Will Capture the Value in AI Biotech?
The final Stanford MS&E435 session with Chai Discovery's Joshua Meier and Anthropic's Eric Kauderer-Abrams: conventional drug development, AI-driven acceleration, and how value may split among pharma, toolmakers, and AI-native biotech.
- #Leadership
Code of Leadership S2E20: Where Does a CTO Have More Freedom—a Startup or a Corporation? With Kirill Evseenko (#Leadership)
An announcement for a conversation with Zvuk CTO Kirill Evseenko about decision-making freedom, scale, responsibility, and the transition from personal control to a system of leaders.
- #Data
The ‘Where Is the Profit from Data, Lebowski?’ Podcast
An invitation to the first episode of a new podcast about data and its value to business, bringing together three authorial perspectives.
- #AI
Stanford MS&E435: Baseten and how unit economics reshapes strategy (Category #AI)
A discussion of Tuhin Srivastava's Stanford talk: from APIs to specialized models, and from renting GPUs to securing compute supply.
- #AI4SDLC
TokenOps: Governing the Budget of an Entire AI Agent Run
A breakdown of Tisha Chawla and Susheem Koul's talk on run-level budgets, a shared cost ledger, STEER before HALT, and the limits of TokenOps' own benchmark.
- #AI
3 AImigo S1E4 Materials: AI Hires AI. How Should We Redesign Tech Interviews? (#AI)
Materials from a 3 AImigo episode about hiring when AI is already on both sides of the interview, and about redesigning interviews as an evaluation system.
- #Management
Code of Leadership S2E19: A CTO's First 90 Days (#Management)
A livestream announcement covering the full transition into a CTO role—from choosing the assignment and agreeing a mutual contract to diagnosis and the first systemic bets.
- #LifeStory
The New Office
A personal note about a new family office with a workspace and a podcast-recording area ahead of a move to London.
- #AI
Stanford MS&E435: Who Chooses the Technology Stack—the Developer or the Coding Agent?
The third Stanford MS&E435 review: how coding agents are becoming a new distribution channel, why open source, documentation, and agentic ergonomics shape stack selection, and where Vercel expects to capture value.
- #AI4SDLC
AI4SDLC: What I Would Do Differently If I Knew Then What I Know Now (#AI4SDLC)
Materials from a talk and panel at Yandex Deep Tech Night, plus an offer to record a director's-cut version of the presentation.
- #LifeStory
Bar Kapibar, Jooie, and Deep Tech Night
A personal note about a packed family-and-conference day before an AI4SDLC talk and a discussion of AI Productivity.
- #AI4SDLC
Microsoft: why faster AI coding did not speed up the team
Microsoft Digital describes the gap between individual coding speed and team productivity, and its move to living specifications: the mechanism and limits of the evidence.
- #Data
A New Podcast, ‘Where Is the Profit from Data, Lebowski?’, About Data and Its Value to Business (#Data)
An announcement for a new podcast about data monetization from the perspectives of product analytics, data-platform architecture, software architecture, and engineering leadership.
- #AI
Yash Patil: A Company's Internal Knowledge Is a Learning Loop
A review of Yash Patil's Stanford MS&E435 lecture: how to turn a company's expert judgment into evals, rewards, and post-training, when specialized models are useful, and why Patil is credible as a practitioner but not a neutral industry oracle.
- #AI
Access to Astra from OpenAI
A short note about receiving access to experiment with Astra from OpenAI.
- #AI
Code of Leadership S2E17: How Can a Mid-Sized Business Use AI When Doing It ‘By the Book’ Is Too Expensive? (#AI)
A livestream announcement about practical AI adoption in a mid-sized business: choosing a use case, building internal capability, and calculating the full cost of entry.
- #Agents
An Illustrated Guide to AI Agents: The Complete Edition (#Agents column)
The complete edition of An Illustrated Guide to AI Agents closes the engineering loop from LLM internals and agent construction to evals, safety, and specialized use cases.
- #AI
3 AImigo Livestream on How AI Is Changing Hiring
A short invitation to a 3 AImigo livestream about how AI is changing hiring.
- #AI
NVIDIA Agrees to Buy Hugging Face: A Neutrality Test (#AI)
Why the proposed $12.93 billion acquisition of Hugging Face would give NVIDIA influence over a critical point of choice in the AI stack, and how to test the platform's promised openness.
- #AI
Sachin Katti: When the Human Becomes the AI System's Bottleneck
A review of Sachin Katti's Stanford MS&E435 lecture: why agents turn inference into a dynamic compute graph, why OpenAI needs heterogeneous infrastructure, and why the desired human bottleneck also creates problems of attention, understanding, verification, and responsibility.
- #Management
Materials from the ‘First 90 Days of a CTO’ Talk
The slide deck and long-form article for the talk on a CTO's first 90 days, plus the threshold for a director's-cut livestream.
- #Management
A CTO's First 90 Days Begin Before the First Day at Work — Management 360 (#Management)
An announcement for a Management 360 talk on transitioning into a CTO role: from choosing the assignment and agreeing a mutual contract to diagnosis and the first systemic changes.
- #Books
Interviewing Yourself: Hypotheses, Verdicts, and a Blue Beard
A book review of individual assessment: why biographical hypotheses can help with self-analysis and why they become riskier in the hands of an external assessor.
- #AI
Stanford MS&E435: Ali Ghodsi Says AGI Is Already Here, but the Company Is Not
A review of Stanford MS&E435 with Ali Ghodsi: why a smart model is not enough without organizational memory, why processes must be redesigned, and which software moats can survive cheaper code.
- #AI4SDLC
Code of Leadership S2E18: The Product Engineer — How the Programmer's Role May Change Over the Next Three Years
An announcement of a conversation with Gleb Mikheev about product engineers, changing expectations for developers, junior training, and keeping up with shifts in software development.
- #Management
Code of Leadership S2E15 Materials: The Last 90 Days at a Company (Rubric #Management)
Video, audio, an interactive deck, a longread, and a written recap for the solo Code of Leadership S2E15 episode on diagnosing a career transition, choosing among three possible outcomes, and handing over responsibility.
- #AI
NVLink Fusion: A Custom XPU, an NVIDIA Rack, and Where MediaTek Fits In (#AI)
A review of NVLink Fusion and NVIDIA's partnership with MediaTek: how a custom XPU connects to NVLink and NVSwitch, where the open UCIe boundary ends, and why NVIDIA's moat may be moving from the GPU to the rack.
- #Education
Live Stream: Developing Junior Engineers in the Age of AI Agents
A short invitation to a live stream about developing junior engineers in the age of AI agents, with a request for audience questions.
- #AI
3 AImigo S1E4: AI Hires AI. How Do We Redesign Tech Interviews?
The fourth 3 AImigo episode explores how AI changes engineering hiring: which signals matter for different roles, how to combine AI-on and AI-off stages, and why engineering judgment matters more than generation speed.
- #AI
Stanford MS&E435: The Scarce Megawatt Behind the AI Factory
A review of Crusoe CEO Chase Lochmiller's lecture: why AI's bottleneck is shifting from GPUs to energised data centres, what a megawatt costs, and where engineering gives way to a vendor pitch.
- #Education
Code of Leadership S2E16: The Junior Engineer After Code — How Do We Develop Engineers When Execution Moves to Agents? (#Education)
An announcement of Code of Leadership S2E16 on developing junior engineers, productive effort, ladders of responsibility, and hiring in a world where the first version of a solution is nearly free.
- #AI
SGLang: How Program Structure Sped Up LLM Inference
A breakdown of the SGLang paper: how RadixAttention, cache-aware scheduling, and structured outputs turned workload knowledge into faster LLM inference.
- #AI
Stanford MS&E435: Inference as a Production System
A review of the second Stanford MS&E435 session: how GPU economics becomes the economics of inference factories, why GPUs and LPUs are combined, and why useful work matters more than tokens burned.
- #Management
Live Stream: The Last 90 Days at a Company
A short invitation to a live stream about the last days at a company, followed by a personal note about collecting an employment record book.
- #AI4SDLC
JetBrains Developer Ecosystem 2026: What 15,509 Developers Say About AI Coding Agents
A review of the JetBrains Developer Ecosystem Survey 2026: the rise of Claude Code and Codex, declines for GitHub Copilot and Cursor, and the limits of a global opt-in sample.
- #AI
Stanford MS&E435: The Economics of the AI Supercycle
A review of Stanford's nine-week MS&E435 seminar: who assembled it, how the course follows the money through the AI stack, what the opening lecture covers, and who benefits from its economic lens.
- #Management
Code of Leadership S2E15: The Last 90 Days at a Company Start Before You Give Notice (#Management)
An announcement of the solo Code of Leadership S2E15 stream about the last 90 days at a company: how to test three career-transition paths and hand over ownership before the final working day.
- #AI
3 AImigo S1E3 Materials: Why Is AI Getting Cheaper While Adoption Gets Harder? (Rubric #AI)
Video, audio, an interactive deck, and fact cards for the third 3 AImigo episode: why higher individual productivity has yet to become systemic ROI, and where scarcity moves as models get cheaper.
- #AI4SDLC
Loop Engineering: An Agent Loop as a Thermostat, Not an Infinite Bash Loop
A breakdown of Kyle Mistele's AI Engineer World's Fair 2026 talk: how control theory turns a blind agent loop into small, reviewable pull requests, and why a human still owns the set point.
- #AI
Bill Gates changes the tone of the AI conversation: this time is different (Rubric #AI)
In April 2023, I [examined](https://t.me/book_cube/1008) Bill Gates’s essay “The Age of AI Has Begun.” His position then was measured: the risks were real but manageable, and AI’s benefits should ultimately outweigh them. The story now has an important second act.
- #AI4SDLC
Episode materials with Anton Kosterin: how do you close the AI-native SDLC loop? (Rubric #AI4SDLC)
The [materials](https://polomodov.tech/research-insights/ai-native-sdlc-playbook/) for episode 29 of Research Insights Made Simple, held on August 27, are ready. Anton Kosterin and I examined Anthropic’s [The AI-Native SDLC Playbook](https://claude.com/blog/the-ai-native-sdlc-playbook): what has to change around coding before agent speed can become delivery speed.
- #Robotics
Sergey Levine: why acrobatic tricks are a poor test for a robot (Rubric #Robotics)
In May, I started the [robotics series](https://t.me/book_cube/4564) by asking where real engineering progress ends and a well-produced demo begins. Sergey Levine’s [interview](https://www.youtube.com/watch?v=9OSbaPjv0Rc), published on August 24, 2026, offers a useful test: a spectacular backflip can reveal less about the future of robots than mundane work with an unfamiliar cup in a new room.
- #AI
McKinsey State of AI 2026: scaling is rising, but the EBIT effect is not (Rubric #AI)
On August 25, McKinsey published its new [State of AI 2026](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai), aptly subtitled “On the road to ROI.” Giving people access to an AI tool is no longer enough: organizations now have to prove that local acceleration can survive the journey through workflows, budgets, and the P&L.
- #BookCube
Join us in 5 minutes to discuss August’s news in an experimental 3 AImigo stream
Join us in 5 minutes to discuss the news from August: 3 AImigo is hosting an [experimental stream](https://www.youtube.com/live/FnrpaV9pjK8) about the month’s most interesting stories.
- #Management
Dominika Rogala on burnout: AI speeds up work — and raises the expected workload (Rubric #Management)
A [post](https://t.me/book_cube/4613) about AI burnout explored the limits of human attention. Dominika Rogala [adds](https://www.youtube.com/watch?v=iJGKH45w4Q8) an organizational layer: AI can make a task cheaper while overloading the work system. The tools got faster — and so did expectations.
- #AI4SDLC
I’m looking for someone to take over AI4SDLC after me (Rubric #AI4SDLC)
I leave T-Bank on August 31, but the AI4SDLC mission remains: transform development processes and move the company toward AI Native. I’m looking for someone with hands-on experience, strong stakeholder skills, and the ambition to carry that work forward.
- #AI4SDLC
Research Insights Made Simple #29: The AI-Native SDLC Playbook with Anton Kosterin (Rubric #AI4SDLC)
Research Insights Made Simple starts in 5 minutes: Anton Kosterin and I will discuss Anthropic’s AI-Native SDLC Playbook and how to redesign the whole delivery lifecycle, not just code generation, around agents.
- #AI
3 AImigo S1E3: August AI news digest (Rubric #AI)
An announcement for the final 3 AImigo stream of August: a new monthly-news format that separates consequential changes for engineers and companies from marketing noise.
Why subscribe
- 01Get notes on key books with practical takeaways and links to the originals
- 02See how the same idea echoes across engineering, management and economics
- 03Be the first to hear about new talks, articles and podcast episodes
- 04Keep a ready-to-use list of recommendations: 'what should I read on X'
How the channel works
Deep reviews
Each post is a notebook for one book: key ideas, context, conclusions and a personal take. Not a blurb — a worked-through view.
Topic tags
Posts are tagged: #Engineering, #Management, #AI, #Economics, #Software, #Leadership and more — easy to find everything on a topic.
Announcements & threads
New talks, tellmeabout.tech articles and Code of Leadership episodes are announced here too. One feed for everything.
Channel sections
Real tags from recent months — frequency reflects the channel's focus: tech, AI and management at the center, but not only.
Post genres
What you'll actually see in the feed.
Engineering book review
From 'Designing Data-Intensive Applications' to fresh AI engineering whitepapers — with a take on what's useful and for whom.
Talk announcement
When a new conference talk comes out — recording, slides, references and a short recap land here.
Practice note
Short observations and ideas: how we build architecture, how culture changes, what works in large orgs.
Whitepapers & research
Reviews of DORA, DevEx, AI4SDLC and other studies — with focus on what's actually applicable.
Who it's for
- Engineers who want depth, not summaries of summaries
- Team leads and managers looking for books in their growth zone
- CTOs and founders holding both the tech and the business context
- Anyone who prefers long, thoughtful posts over a news feed
Subscribe
One post every few days, zero ads, thousands of readers as of May 2026 — join if you learn through books.
Open Book Cube