Book Cube: 2026, page 5
Book Cube publications from 2026, page 5: bilingual notes, sources, and original Telegram posts.
- #PlatformEngineering
Kubernetes: too complex? Materials from DevOps Deflope No. 62 (Category #PlatformEngineering)
Materials from DevOps Deflope episode 62: Kubernetes complexity, internal platforms, and the trust boundaries for AI agents in a cluster.
- #AI4SDLC
Developer Productivity for Humans: four tensions of AI
How AI shifts work between stages and people, affects debt and learning: a continuation of Google's developer productivity series and the authors' recommendations.
- #Research
How I Read Whitepapers Now: Marginal Notes and AI
A personal note on reading research papers with marginal annotations and discussing them with Codex/Claude.
- #AI4SDLC
How Vercel Built d0: An Agent's Evolution and Questions About Its Results
The evolution of Vercel's analytics agent d0, from a large prompt and specialist chain to a file-based environment, skills, and the eve framework—and the open questions about answer quality and accumulated knowledge.
- #AI4SDLC
YC Paper Club: What Turns a Model into a Working Agent (Category #AI4SDLC)
Four engineering perspectives on agent harnesses: tools and memory, Prime Agent, local OpenJarvis, and the QM internal platform for dozens of personal agents.
- #AI4SDLC
How AI Will Change Software Development: Organized Programming #92 Materials (Category #AI4SDLC)
Materials from a conversation with Kirill Mokevnin about how AI changes programmers’ work, team design, internal platforms, impact measurement, and engineering education.
- #Leadership
Episode Materials: CTO Freedom in Startups and Corporations with Kirill Evseenko (Category #Leadership)
Recording and recap of Code of Leadership S2E20 with Zvuk CTO Kirill Evseenko: scaling START, technology economics, influence through managers, and engineering careers.
- #Museum
Science Museum Souvenir Book (Category #Museum)
The London Science Museum souvenir book echoes the exhibition's logic: domains, chronology, and inventions represented in the collection.
- #Data
Where’s the Data Profit, Lebowski? Episode One Materials (Category #Data)
Recording, companion article, and recap of the first episode with Andrey Tsybin, Nikolay Golov, and Alexander Polomodov: who buys data, what they pay for, and what remains after costs.
- #AI4SDLC
Habitat: the evolution of OpenAI’s storage layer (Category #AI4SDLC)
Habitat’s evolution from a library to a Python service and Rust: operational control, a constrained API, analytics isolation, and latency under load.
- #AI4SDLC
Codex: Why Cheaper Rewrites Still Need Architecture (Category #AI4SDLC)
Tibo Sottiaux's path from DeepMind to Codex: how agents make changes cheaper and why agreement on system boundaries becomes more important.
- #Leadership
Code of Leadership: the Livestream with Kirill Evseenko Is Live
An invitation to a livestream with Zvuk CTO Kirill Evseenko about a CTO's career and freedom in startups and corporations.
- #Research
[2/2] DistServe: Parallelism, Queues, and GPU Balancing (Category #Research)
The second DistServe breakdown: tensor and pipeline parallelism, queues, workload simulation, and balancing GPUs for a model, request profile, and SLO.
- #Research
[1/2] DistServe: Why Separate Prefill and Decode (Category #Research)
A breakdown of DistServe: separate GPU pools for prefill and decode, KV-cache transfer, topology, and goodput under specified SLOs.
- #AI
3 AImigo: the episode about junior engineers is live
A short update that the 3 AImigo episode about junior engineers is live.
- #Leadership
Episode materials: the first 90 days as CTO
Materials for solo Code of Leadership episode 77: choosing the role, agreeing on authority, first-month diagnosis, and initial changes. Recording, slides, longread, and recap.
- #Management
Randy Shoup on eBay: Engineering Sped Up, the System Did Not
A breakdown of Randy Shoup's LeadDev London 2026 talk: how, according to the speaker, eBay doubled engineering productivity with a standard DevOps playbook yet failed to change centralized planning, the feature factory, and what he describes as a pathological culture.
- #AI4SDLC
AI4SDLC at IT Picnic: Talk Materials (Category #AI4SDLC)
Slides, recording and an edited recap of Alexander Polomodov’s final talk representing T-Bank, taking stock of AI4SDLC as he had developed it.
- #Architecture
ArchDays in the AI Era (Category #Architecture)
How architecture conferences help rethink engineering processes and the architect's role in the AI era.
- #Leadership
Episode Materials: Product Engineering with Gleb Mikheev (Category #Leadership)
Recording and recap of Code of Leadership episode 76: product ownership, new constraints as development accelerates, and engineering growth when working with agents.
- #AI
Stanford MS&E435: From Megawatts to Molecules — the Complete Course in Nine Reviews
A closing post on Stanford MS&E435: why the course offers a useful map of AI economics, with links to all nine reviews—from GPUs and data centers to coding agents and drug discovery.
- #AI
3 AImigo S1E5: A Junior Engineer Without Simple Tasks — How Do You Enter IT in the AI Era?
A preview of the fifth 3 AImigo episode on how an aspiring engineer can enter the profession when AI agents are taking over traditional entry-level tasks.
- #Management
A CTO's First 90 Days: Extended Livestream
An invitation to an extended version of the talk on a CTO's first 90 days, followed by a live Q&A.
- #AI
PyTorch as a Portability Layer: Why Cambricon and Ant Group Joined
Why Cambricon and Ant Group joining the PyTorch Foundation is not a purchase of control over the code, but an attempt to reduce the software cost of moving away from CUDA—and which technical signals will reveal whether it works.
- #AI4SDLC
Code of Leadership S2E18: A Livestream About Product Engineers
A short invitation to a livestream with Gleb Mikheev about how the role of programmers will change and what the product-engineer concept means.
- #AI4SDLC
Ollama: How Agents Are Changing Open-Model Economics
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
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
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?
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
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
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
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?
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
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
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.