Book Cube: 2026, page 3
Book Cube publications from 2026, page 3: bilingual notes, sources, and original Telegram posts.
- #Engineering
Pavel Golubev FDE Livestream Rescheduled
A date correction for the conversation with Pavel Golubev about forward deployed engineers.
- #Data
AI and Data Platforms: Research Insights Made Simple №37 Materials
A conversation with Nikolay Golov about data platform approaches, zero-ETL, and engineering trade-offs.
- #AI4SDLC
3 AImigo S1E9: Boundaries of Autonomy — Episode Materials
Materials from a discussion of agent delegation, approvals, and the full cost of an accepted task.
- #AI4SDLC
Live: What Does an Agent Harness Contribute?
An invitation to discuss a study of planning, tools, and context management for coding agents.
- #AI4SDLC
Factory: Engineers Become Managers — Who Can Still Check Their Agents’ Work?
Davis Palmie’s talk on software factories, environment readiness, and engineering judgment when managing agents.
- #Books
Harness Engineering: Familiar Ideas in One Book
Nicole Koenigstein’s first two chapters: familiar ideas, task state, and questions about when harness components help.
- #AI4SDLC
Research Insights #36: Harnesses for Long-running Development
Episode materials on planners, generators, evaluators, and the limits of autonomous application development.
- #Data
AI and Data Platforms: Live with Nikolay Golov
An invitation to a conversation with Nikolay Golov about adding AI to data platforms.
- #AI4SDLC
Meet Pi: The Minimalist, Self-Modifying Coding Agent
Mario Zechner and Armin Ronacher on a small agent core, extensions, and control over the workflow.
- #AI4SDLC
Research Insights #35 materials: an environment for agents
Episode materials on OpenAI harness engineering: project knowledge, tools, architectural checks, and technical debt.
- #ForKids
Pasha and Dad
A book about Pasha and his dad: family sketches, reading with Kirill, and a personal postscript.
- #Management
FDE: who is responsible for making AI work for the customer?
The October 14 Code of Leadership livestream with Pavel Golubev: AI implementation, project boundaries, and FDE management.
- #AI4SDLC
Harness design for coding agents: what does the harness contribute?
An experimental comparison of planning, tools, and context management in coding agents.
- #Data
AI and the data platform: connecting AI to all an organization’s data
The October 12 livestream with Nikolay Golov on operational data, analytics, Lakehouses, and agents.
- #Books
The Forward Deployed Engineer — Paden Gayle
The first two chapters on FDE responsibility, stakeholder alignment, and the economics of implementation.
- #AI
YC Paper Club: what comes after LLM + GPU?
Optical computing, neuromorphic chips, and living neurons: research bets and demonstration limits.
- #Books
The Man from the Future: The Visionary Life of John von Neumann
Reflections on John von Neumann’s biography: computing, game theory, physics, and self-reproducing machines.
- #AI4SDLC
Research Insights #34 materials: long-running agents and handoffs
Episode materials on session handoffs, completion criteria, and evaluating a harness.
- #AI4SDLC
Research Insights livestream: long-running application development
An invitation to a livestream on Anthropic’s March article about harnesses for long-running application development.
- #Personal
A charity auction: breakfast together
A breakfast meeting auction on Tolk in support of the Nit Dobra charity.
- #Management
Code of Leadership #84 materials: does a developer become a manager in the AI era?
A conversation with Andrey Dmitriev about useful tasks, responsibility, and the agent lifecycle.
- #AI4SDLC
Harness design for long-running autonomous application development
Anthropic’s Planner, Generator, and Evaluator: acceptance, cost, and simplification as models improve.
- #AI4SDLC
Research Insights #33 materials: SWE-agent
Episode materials on how tools, interfaces, and feedback change an agent’s results.
- #AI4SDLC
Justin Reock: code is easier to change, harder to release confidently
DX observations on maintainability, change confidence, and PR growth; what to verify after adopting AI.
- #Leadership
Why a manager returns to code — episode materials (Series #Leadership)
Materials for Code of Leadership #82 with Nikita Belokopytov: returning to code, management skills, and the limits of agent autonomy.
- #AI4SDLC
Harness engineering: how an experimental team at OpenAI reorganized development around agents for an internal product (Series #AI4SDLC)
OpenAI’s experience with repository knowledge, verifiable architecture, agent tools, and Symphony. An invitation to Research Insights #35.
- #AI4SDLC
Research Insights #34: handing work over between agent sessions
An invitation to Research Insights #34 on handing work over between sessions of the same agent, based on Anthropic’s article.
- #AI4SDLC
Warp: you corrected the agent. What did the system learn? (Series #AI4SDLC)
How Warp proposes turning engineers’ corrections into skill updates, and why those instructions also need verification.
- #AI4SDLC
Anthropic’s agent harness: handing work over between coding sessions (Series #AI4SDLC)
Handing work over between agent sessions: logs, Git, requirements, and verified state. An Anthropic article discussion with an annotated PDF.
- #AI4SDLC
Developers are becoming managers: a livestream with Andrey Dmitriev
An invitation to a livestream with Andrey Dmitriev from JUG.RU on why developers are becoming managers.
- #AI4SDLC
Conductor: how to conduct an orchestra of agents (Series #AI4SDLC)
Charlie Holtz on managing multiple agents, mandatory human review, team knowledge, and the cost of switching attention.
- #Leadership
Episode materials: how an engineer learns to negotiate — Sergey Kiselev (Series #Leadership)
Materials for Code of Leadership #83: platform development through collaboration, team autonomy, hiring, and incident follow-up.
- #AI4SDLC
SWE-agent: how an interface helps a model work with code (Series #AI4SDLC)
SWE-agent and its ACI: SWE-bench Lite results, the cost of constraints, and the move to mini-swe-agent. Includes an annotated PDF.
- #AI4SDLC
SWE-agent: how the interface changes the result / Research Insights Made Simple #33 (Series #AI4SDLC)
A livestream on SWE-agent: code search and editing, feedback, context management, and the results of the 2024 experiments.
- #AI4SDLC
Factory and HumanLayer: how much autonomy should agents have? (Series #AI4SDLC)
How Factory and HumanLayer approach agent autonomy, delivery costs, code review, and team readiness.
- #AI
One designer and hundreds of assets (Category #AI)
What caught my attention in Vincent Wendy's talk about AI Engineer was the designer's willingness to change his processes and build his own tools when the workload becomes too large to handle manually.
- #AI4SDLC
3 AImigo S1E8: AI-native companies — episode materials (Category #AI4SDLC)
Recordings, audio editions, an edited recap, and a longread accompanying the conversation with Aleksey Litvinov and Evgeny Sergeev about people and agents, process redesign, and automation economics.
- Books
While preparing to move, I started sorting through my books and clearing out my library.
A brief recommendation of Scott Page’s “The Model Thinker” and a recollection of his Coursera course, which started the author’s enthusiasm for online learning.
- #AI
Stanford CME295, Lecture 1: How Text Becomes Computation (Category #AI)
Stanford CME295’s first lecture explains tokens, embeddings, attention and the Transformer through an end-to-end translation example, with advice on who will benefit and what prior knowledge helps.
- #ForKids
Kamil Sees with His Hands (Category #ForKids)
A recommendation of a book about five-year-old Kamil, who is blind: humor, family love and a starting point for conversations with a child.
- #Data
Finding value in your own data: pricing, customers, and assortment — episode two materials (Category #Data)
Materials from episode two of Where’s the Profit in Data, Lebowski? Andrey Tsybin, Nikolay Golov, and Alexander Polomodov discuss pricing, customer profitability, assortment, and how to assess the effects of changes.
- #AI4SDLC
How AI changes the tech lead's role: roundtable recording (Category #AI4SDLC)
The Podlodka Techlead Crew roundtable on tech lead responsibility, AI economics, reviewing changes, and training engineers. A written recap and the author's position prepared before the discussion are also available.
- #AI
Stanford CME295: Getting into the Foundations of LLMs (Category #AI)
A recommendation of Afshine and Shervine Amidi’s course: accessible explanations of how LLMs work, the 2025 recordings, and the updated Autumn 2026 syllabus.
- #Leadership
How Engineers Learn to Negotiate: Live with Sergey Kiselev
An invitation to a livestream with Sergey Kiselev, head of devplatform at MWS, about how engineers learn to negotiate.
- #AI
Anthropic: Who Will Build the Next AI
How research automation could accelerate new models, why the trend points toward 2027, and what still needs measuring before we can talk about autonomy and control.
- #Management
3 AImigo S1E8: AI-native — what does it mean for a company?
An announcement for the October 2, 2026 3 AImigo live stream on AI-native companies with Evgeny Sergeev, Alexey Litvinov, and Alexander Polomodov.
- #AI
AMD Agrees to Acquire World Labs for $8.2 Billion (Category #AI)
AMD’s planned World Labs acquisition: spatial models, robot simulation, hardware feedback, and what to watch before judging the deal.
- #Leadership
Why Return to Coding as a Manager? Live with Nikita Belokopytov
Join a live conversation with Nikita Belokopytov about his career and why a manager might return to coding.
- #Leadership
Episode Materials: Leading in an Unfamiliar Field with Leonid Chernyy (Category #Leadership)
Recording and summary of Code of Leadership S2E23: Leonid Chernyy on moving from games to data, user habits, disagreeing with managers, and CDO authority.
- #AI
Kai Lentit on AI-Company Executives
Kai Lentit’s satirical take on the executives leading AI companies.