Book Cube: 2026, page 1
Book Cube publications from 2026, page 1: bilingual notes, sources, and original Telegram posts.
- #AI4SDLC
When does a team need Warp’s “software factory”? (Series #AI4SDLC)
How Warp counts recurring agent mistakes and tests changes to shared rules.
- #Conference
AI Dev Conf 2026 (Series #Conference)
An invitation to AI Dev Conf talks and workshops on November 26 and 28.
- #Management
Which task should you start AI adoption with? Code of Leadership with Pavel Popkov (Series #Management)
A conversation with Pavel Popkov about choosing a first task for an AI pilot in retail.
- #AI4SDLC
What Diogo Almeida wants to put inside an ordinary if
Diogo Almeida’s examples of semantic checks in code, linters and agent memory.
- #Personal
The people you know and why they matter
Before leaving for London, the author thanks the friends and colleagues he has learned from.
- #Management
Live with Vasiliy Gigauri on the responsibilities of a CTO
An invitation to a live discussion with Vasiliy Gigauri on how a CTO’s responsibilities grow.
- #DeveloperProductivity
Developer productivity / how DX measures it (Series #DeveloperProductivity)
A preview of a live discussion of DX Core 4, the AI Measurement Framework and CAFE(S).
- #Management
From products to needs: how an organization changes — episode materials (Series #Management)
Recording, slides and notes on several product teams working on a single purchase.
- #AI4SDLC
DX Q3 2026 and the cost of trusting code (Series #AI4SDLC)
Margin notes on DX’s report covering PR weights, review queues and the cost of working with agents.
- #Management
Live stream on the shift from products to needs
An invitation to the follow-up stream on organizational redesign.
- #Books
The Russian North — Anna Korob (Series #Books)
Anna Korob’s photo book on villages and architecture in the Arkhangelsk region.
- #Management
From products to needs: how an organization changes / Code of Leadership S2E31 (Series #Management)
A live discussion of a car purchase as a customer journey shared across product teams.
- #AI4SDLC
AI sped up development: how can you tell? (Series #AI4SDLC)
Talk materials on measuring AI’s impact from an initial hypothesis through to a customer outcome.
- #AI
Stanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 4 – Reinforcement Learning with LLMs (Series #AI)
How an answer’s reward changes token probabilities in REINFORCE, PPO and GRPO.
- #AI4SDLC
3 AImigo S1E14 token budget stream rescheduled
A new date for the token budget stream and an invitation to submit questions.
- #AI4SDLC
How incident.io measures AI spending (Series #AI4SDLC)
AI spend per engineer and per effort point at incident.io, alongside production incident rates.
- #AI4SDLC
Research Insights #47 Materials: Does AGENTS.md Help the Agent? (Series #AI4SDLC)
Episode materials on checking whether repository instructions improve outcomes as well as compliance.
- #Books
Contemporary Architecture in China: Buildings and Projects 2000–2020 (Series #Books)
A personal look through an architecture photo book, from Shanghai’s skyline to the wall of a museum in Ningbo.
- #AI4SDLC
Research Insights #46 Materials: How Much Harness Does a Strong Model Need? (Series #AI4SDLC)
Episode materials on file tools, subagents, context compaction, and execution environments.
- #AI4SDLC
3 AImigo S1E14: A Token Budget / How Much Does AI in Development Cost? (Series #AI4SDLC)
A live discussion about planning AI spending and calculating the cost of an accepted change.
- #AI4SDLC
Research Insights #45 Materials: Model or Harness? (Series #AI4SDLC)
Episode materials on separating model and harness effects and checking benchmark failures.
- #Agent
[2/2] When One Analyst’s Memory Helps the Whole Team (Series #Agent)
How analytics platforms turn individual corrections and query patterns into shared guidance.
- #AI4SDLC
Does AGENTS.md Help the Agent? Live Research Insights
A live episode on the effect of repository context files on agent behavior, cost, and task success.
- #Agent
[1/2] MemCurrent: What an Agent Carries Over from the Last Session (Series #Agent)
Databricks’ two-layer memory architecture, its benchmarks, and the author’s notes on the ablations.
- #Management
From Developer to CTO and COO of Manychat: Episode Materials (Series #Management)
Dmitry Kushnikov on returning to coding, scaling teams, and taking on operations.
- #AI4SDLC
Live Research Insights: Harbor Adapters and Harbor-Index
A live invitation to discuss the large-scale Harbor benchmark experiment.
- #AI
Do Agents Dream of Electric Sheep? How Claude Revisits Its Memory (Series #AI)
Anthropic’s background memory consolidation and questions about how to evaluate it.
- #Software
Gitleaks and the Secrets Git Remembers (Series #Software)
The history of Gitleaks, what local scanning covers, and where Betterleaks takes it further.
- #AI4SDLC
Live Research Insights: Beyond the Model
A live invitation to discuss the study of harness effects in software engineering agents.
- #Management
[2/2] The AI-Native Organization: From Signal to Action (Series #Management)
An equipment failure illustrates how an AI-native company could connect detection, decisions, execution, and feedback.
- #AI
[1/2] Organizing Intelligence: The Economics of Coordination (Series #AI)
A theoretical model of firms that can rent copies of AI and of what happens when coordination scales.
- #Management
Code of Leadership: How a CTO’s Responsibilities Grow, with Vasiliy Gigauri (Series #Management)
An episode announcement on engineering leadership, platform reliability, and decisions at board level.
- #Software
“Video.js: The Documentary” and the Cost of Maintaining Open Source (Series #Software)
A documentary on what happens when a widely used project loses its maintainers.
- #Management
Code of Leadership S2E29 Materials: Organizational Redesign and Handing Over Authority (Series #Management)
Episode materials on dividing a large engineering organization and handing decisions to new CTOs.
- #AI4SDLC
Live: 3 AImigo on Infrastructure for Agentic Development
A live invitation to episode 13 of 3 AImigo.
- #AI4SDLC
Research Insights #44 Materials: Randomness in Agent Evals (Series #AI4SDLC)
Episode materials on repeat runs and distinguishing small improvements from evaluation noise.
- #AI4SDLC
Harbor: How to Tell Why an Agent Failed a Task (Series #AI4SDLC)
Harbor’s benchmark adapters, model and harness comparisons, and notes on auditing evaluators.
- #AI4SDLC
IDE vNext: Who Will Build a Home for AI Agents? (Series #AI4SDLC)
Materials from the DotNext roundtable on development environments for engineers and agents.
- #AI4SDLC
AI Dev Live 2026: What to Watch and How to Measure AI’s Impact (Series #AI4SDLC)
Three talks to start with and a session on measuring AI’s effect on development.
- #Management
Live: Redesigning an Organization of 1,000 Engineers
A live invitation to hear how the author redesigned his engineering division.
- О канале
A Guide to Book Cube
A guide to the channel’s topics and the author’s other projects.
- #Books
American National Parks: A Book to Leaf Through (Series #Books)
A personal note about enjoying a photo book on US national parks.
- #AI4SDLC
What Does a Reviewer Check When Anthropic Merges 30,000 Changes a Day? (Series #AI4SDLC)
A talk about giving code reviewers evidence they can examine and challenge.
- #Management
Organizational Redesign for a Division of 1,000 Engineers
A solo episode announcement on dividing a large engineering organization into five units and handing authority over to CTOs.
- #PlatformEngineering
3 AImigo S1E13: Infrastructure for Agentic Development
An episode announcement on how CI, review, and access management change under workloads created by agents.
- #Books
Corporate [Trans]formation: Strengthening a Business by Developing People
A review of the Borisovs' book on HR processes, employee learning, and management maturity.
- #AI4SDLC
State of AI4SDLC: How Software Development Changes as Code Becomes Easier to Write
The DotNext keynote recording, summary, and slides on delivery, migrations, and knowledge that should outlive the code.
- #Engineering
[3/3] Octoverse 2026: Agents, Models, and Development Workflows
Part three of a look at GitHub's report, covering delegation to agents, model selection, review, and security.
- #Book
Code of Leadership: How to Lead Engineers by Example When Agents Write the Code
A working plan for a 20-chapter book on a leader's practice, delegation, and change in engineering teams.
- #Engineering
[2/3] Octoverse 2026: Languages, Industries, and Open Source
Part two of a look at GitHub's report, covering languages, industry classification, and open-source growth.